Search

Our recent phase 2 randomized clinical trial (I-SABR, NCT03110978) demonstrated improved event-free survival (EFS) from combining stereotactic ablative radiotherapy (SABR) with immune checkpoint inhibitor therapy for early-stage non-small cell lung cancer (NSCLC) relative to SABR alone. However, not every patient benefits from immunotherapy. We report here a secondary analysis in which clinical-radiomics, with machine learning, was developed into a model to identify patients who would or would not benefit from immunotherapy. Subjects were 141 patients with early-stage NSCLC enrolled in the I-SABR trial, 101 in the discovery and 40 in the validation cohort. We used the discovery cohort to develop the I-SABR-SELECT framework to model treatment outcomes and inform patient selection for combining immunotherapy with SABR. We extracted radiomics patterns characterizing the tumor/peritumoral and lung regions and the angiogenesis network surrounding the tumor. Radiomics features were harmonized, qualified, and integrated with clinical factors for downstream selection to mitigate model overfitting. A random survival forest algorithm was applied to model relationships between patient characteristics and treatment outcome separately for I-SABR and SABR-only. Counterfactual reasoning was used to assess treatment effects and optimize selection. The model was evaluated separately in the discovery and validation cohorts and in an independent group of patients treated on the STARS trial of SABR for early-stage NSCLC. Overall, the model recommended that 46 of the 141 (33%) patients enrolled in I-SABR switch treatments (34 of 75 [45%] in the SABR-only arm and 12 of 66 [18%] in the I-SABR arm). Patients treated according to this recommendation achieved significantly improved EFS in both arms during model discovery and validation. Stratified by this recommendation, patients who received I-SABR showed an EFS interval 1.1 to 1.6 times longer than those who did not receive immunotherapy. Notably, patients who were treated according to the I-SABR-SELECT recommendation had improved EFS (hazard ratio = 22.8, P < 0.001) compared with matched counterparts who did not receive the model-recommended treatment. Conversely, when the model recommended SABR-only, no difference in EFS was observed between patients given SABR-only vs those given I-SABR. In the benefit stratum by the model, the average immunotherapy effect was more than two-fold greater than in the randomized trial. Having worse performance status, a less complex angiogenesis network, and larger tumors were associated with more benefit from combining immunotherapy with SABR. I-SABR-SELECT provides an individualized approach for guiding who needs immunotherapy combined with SABR for early-stage NSCLC. [ABSTRACT FROM AUTHOR]

We develop a machine learning (ML) model using electrocardiography (ECG) to predict myocardial blood flow reserve (MFR) and assess its prognostic value for major adverse cardiovascular events (MACEs). Using 3,639 ECG-positron emission tomography (PET) and 17,649 ECG-single-photon emission computed tomography (SPECT) data pairs, the ML model is trained with a swarm intelligence approach and support vector regression (SVR). The model achieves a receiver-operator curve (ROC) area under the curve (AUC) of 0.83, with a sensitivity and specificity of 0.75. An ECG-MFR value below 2 is significantly associated with MACE, with hazard ratios (HRs) of 3.85 and 3.70 in the discovery and validation phases, respectively. The model's C-statistic is 0.76, with a net reclassification improvement (NRI) of 0.35. Validated in an independent cohort, the ML model using ECG data offers superior MACE prediction compared to baseline clinical models, highlighting its potential for risk stratification in patients with coronary artery disease (CAD) using the accessible 12-lead ECG., Competing Interests: Declaration of interests The authors declare no competing interests., (Copyright © 2024 The Author(s). Published by Elsevier Inc. All rights reserved.)

Background: Only around 20-30% of patients with non-small-cell lung cancer (NCSLC) have durable benefit from immune-checkpoint inhibitors. Although tissue-based biomarkers (eg, PD-L1) are limited by suboptimal performance, tissue availability, and tumour heterogeneity, radiographic images might holistically capture the underlying cancer biology. We aimed to investigate the application of deep learning on chest CT scans to derive an imaging signature of response to immune checkpoint inhibitors and evaluate its added value in the clinical context., Methods: In this retrospective modelling study, 976 patients with metastatic, EGFR/ALK negative NSCLC treated with immune checkpoint inhibitors at MD Anderson and Stanford were enrolled from Jan 1, 2014, to Feb 29, 2020. We built and tested an ensemble deep learning model on pretreatment CTs (Deep-CT) to predict overall survival and progression-free survival after treatment with immune checkpoint inhibitors. We also evaluated the added predictive value of the Deep-CT model in the context of existing clinicopathological and radiological metrics., Findings: Our Deep-CT model demonstrated robust stratification of patient survival of the MD Anderson testing set, which was validated in the external Stanford set. The performance of the Deep-CT model remained significant on subgroup analyses stratified by PD-L1, histology, age, sex, and race. In univariate analysis, Deep-CT outperformed the conventional risk factors, including histology, smoking status, and PD-L1 expression, and remained an independent predictor after multivariate adjustment. Integrating the Deep-CT model with conventional risk factors demonstrated significantly improved prediction performance, with overall survival C-index increases from 0·70 (clinical model) to 0·75 (composite model) during testing. On the other hand, the deep learning risk scores correlated with some radiomics features, but radiomics alone could not reach the performance level of deep learning, indicating that the deep learning model effectively captured additional imaging patterns beyond known radiomics features., Interpretation: This proof-of-concept study shows that automated profiling of radiographic scans through deep learning can provide orthogonal information independent of existing clinicopathological biomarkers, bringing the goal of precision immunotherapy for patients with NSCLC closer., Funding: National Institutes of Health, Mark Foundation Damon Runyon Foundation Physician Scientist Award, MD Anderson Strategic Initiative Development Program, MD Anderson Lung Moon Shot Program, Andrea Mugnaini, and Edward L C Smith., Competing Interests: Declaration of interests NIV receives consulting fees from Sanofi, Regeneron, Oncocyte, and Eli Lilly; and research funding from Mirati, outside the submitted work. SHL reports research funding from STCube Pharmaceuticals, Beyond Spring Pharmaceuticals, and Nektar Therapeutics; being on an advisory board for AstraZeneca and Creatv Microtech; and receiving consultation fees from XRAD Therapeutics, all outside the submitted work. PPL reports personal fees from Viewray and AstraZeneca; personal fees and non-financial support from Varian; and personal fees from Genentech, outside the submitted work. SG reports research support from AstraZeneca, BMS, and Millenium Pharmaceuticals, all outside the submitted work. JYC reports research funding from BMS-MDACC and consultation fees from Legion Healthcare Partners. MFG reports research support from Varian Medical Systems and RefleXion Medical. HAW reports research funding from ACEA Biosciences, Arrys Therapeutics, AstraZeneca/Medimmune, BMS, Clovis Oncology, Genentech/Roche, Merck, Novartis, SeaGen, Xcovery, and Helsinn; being on an advisory board for AstraZeneca, Blueprint, Mirati, Merck, and Genentech/Roche; and has leadership roles with the International Association for the Study of Lung Cancer, and ECOG-ACRIN. JWN reports honoraria from CME Matters, Clinical Care Options Continuing Medical Education (CME), Research to Practice CME, Medscape CME, Biomedical Learning Institute CME, MLI Peerview CME, Prime Oncology CME, Projects in Knowledge CME, Rockpointe CME, MJH Life Sciences CME, Medical Educator Consortium, and HMP Education; consulting or advisory roles for AstraZeneca, Genentech/Roche, Exelixis, Jounce Therapeutics, Takeda Pharmaceuticals, Eli Lilly, Calithera Biosciences, Amgen, Iovance Biotherapeutics, Blueprint Pharmaceuticals, Regeneron Pharmaceuticals, Natera, Sanofi/Regeneron, D2G Oncology, Surface Oncology, Turning Point Therapeutics, Mirati Therapeutics, Gilead Sciences, and AbbVie; and research funding from Genentech/Roche, Merck, Novartis, Boehringer Ingelheim, Exelixis, Nektar Therapeutics, Takeda Pharmaceuticals, Adaptimmune, GSK, Janssen, and AbbVie. H-SL reports research funding from Samyang Biopharmaceutical USA. VV reports consulting fees from BMS, Merck, Novartis, Amgen, Foundation Medicine, and AstraZeneca. YL reports research funding from Merck, MacroGenics, Tolero Pharmaceuticals, AstraZeneca, Vaccinex, Blueprint Medicines, Harpoon Therapeutics, Sun Pharma Advanced Research, Bristol Myers Squibb, Kyowa Pharmaceuticals, Tesaro, Bayer HealthCare, Mirati Therapeutics, and Daiichi Sankyo; has been on scientific advisory boards for AstraZeneca Pharmaceuticals, Janssen Pharmaceutical, Lilly Oncology, and Turning Point Therapeutics; has received consultation fees from AstraZeneca; and has received honoraria from Clarion Health Care. MP reports research funding from Novartis Institutes for Biomedical Research. XLe reports research funding from Eli Lilly, EMD Serono, Regeneron, and Boehringer Ingelheim; and consultant fees from EMD Serono (Merck KGaA), AstraZeneca, Spectrum Pharmaceutics, Novartis, Eli Lilly, Boehringer Ingelheim, Hengrui Therapeutics, Janssen, Blueprint Medicines, Sensei Biotherapeutics, and AbbVie, outside the submitted work. YYE discloses research support from AstraZeneca, Takeda, Eli Lilly, Xcovery, Tuning Point Therapeutics, Blueprint, Elevation Oncology, Spectrum, and Nuvalent; having advisory roles for AstraZeneca, Eli Lilly, Takeda, Specturm, Bristol Myers Squibb, and Turning Point Therapeutics; and accommodation expenses from Eli Lilly. MVN has been on scientific advisory boards for Mirati, Merck/MSD, and Genentech; and has received research funding from Mirati, Novartis, Checkmate, Alaunos/Ziopharm, AstraZeneca, Pfizer, and Genentech. FS reports consulting fees and advisory roles from Amgen, AstraZeneca Pharmaceuticals, Novartis, BeiGene, Tango Therapeutics, Calithera Biosciences, Navire Pharma, Medscape, Intellisphere, Guardant Health, and BergenBio; speaker fees from BMS, RV Mais Promoção e Eventos, Visiting Speakers Programme in Oncology at McGill University and the Université de Montréal, AIM Group International, and ESMO; fees for travel, food, and beverages from Tango Therapeutics, AstraZeneca Pharmaceuticals, Amgen, Guardant Health, and Dava Oncology; stock or stock options in BioNTech and Moderna; research grants (to institution) from Amgen, Mirati Therapeutics, Boehringer Ingelheim, Merck & Co, and Novartis; study chair funds (to institution) from Pfizer; and research grants (spouse, to institution) from Almmune. CMG reports fees for advisory committees from AstraZeneca, Bristol Myers Squibb, Jazz Pharmaceuticals, and Monte Rosa Therapeutics; research support from AstraZeneca; and speaker's fees from AstraZeneca and Beigene. TC reports speaker fees and honoraria from The Society for Immunotherapy of Cancer, Bristol Myers Squibb, Roche, Medscape, and PeerView; having an advisory role or receiving consulting fees from AstraZeneca, Bristol Myers Squibb, EMD Serono, Merck & Co, Genentech, and Arrowhead Pharmaceuticals; and institutional research funding from AstraZeneca, Bristol Myers Squibb, and EMD Serono. IIW reports grants and personal fees from Genentech/Roche, Bayer, Bristol Myers Squibb, AstraZeneca, Pfizer, HTG Molecular, Merck, Guardant Health, Novartis, and Amgen; personal fees from GSK, Flame, Sanofi, Daiichi Sankyo, Oncocyte, Janssen, MSD, and Platform Health; and grants from Adaptimmune, Adaptive, 4D, EMD Serono, Takeda, Karus, Iovance, Johnson & Johnson, and Akoya outside the submitted work. JDH is on the Scientific Advisory Board of Imagion Biosystems. DLG reports honoraria for scientific advisory boards from AstraZeneca, Sanofi, Alethia Biotherapeutics, Menarini, Eli Lilly, 4D Pharma, and Onconova; and research support from Janssen, Takeda, Astellas, Ribon Therapeutics, NGM Biopharmaceuticals, Boehringer Ingelheim, Mirati Therapeutics, and AstraZeneca. JVH reports being on scientific advisory boards for AstraZeneca, Boehringer Ingelheim, Genentech, GlaxoSmithKline, Eli Lilly, Novartis, Spectrum, EMD Serono, Sanofi, Takeda, Mirati Therapeutics, BMS, and Janssen Global Services; receiving research support from AstraZeneca, Takeda, Boehringer Ingelheim, and Spectrum; and receiving licensing fees from Spectrum. JZ reports research funding from Merck, Johnson & Johnson, and Novartis; and consultant fees from BMS, Johnson & Johnson, AstraZeneca, Geneplus, OrigMed, Novartis, and Innovent, outside the submitted work. CCW reports research support from Medical Imaging and Data Resource Center from NIBIB/University of Chicago and royalties from Elsevier. All other authors declare no competing interests., (Copyright © 2023 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY-NC-ND 4.0 license. Published by Elsevier Ltd.. All rights reserved.)

Survival models exist to study relationships between biomarkers and treatment effects. Deep learning-powered survival models supersede the classical Cox proportional hazards (CoxPH) model, but substantial performance drops were observed on high-dimensional features because of irrelevant/redundant information. To fill this gap, we proposed SwarmDeepSurv by integrating swarm intelligence algorithms with the deep survival model. Furthermore, four objective functions were designed to optimize prognostic prediction while regularizing selected feature numbers. When testing on multicenter sets (n = 1,058) of four different cancer types, SwarmDeepSurv was less prone to overfitting and achieved optimal patient risk stratification compared with popular survival modeling algorithms. Strikingly, SwarmDeepSurv selected different features compared with classical feature selection algorithms, including the least absolute shrinkage and selection operator (LASSO), with nearly no feature overlapping across these models. Taken together, SwarmDeepSurv offers an alternative approach to model relationships between radiomics features and survival endpoints, which can further extend to study other input data types including genomics., Competing Interests: B.A.-L. declares commercial interest in Exscientia and AstraZeneca and is/was a consultant/scientific advisory board member for GlaxoSmithKline (GSK), Open Targets, Astex Pharmaceuticals, and Astellas Pharma, and is an ex-employee of Inpharmatica Ltd., all outside of the submitted work. J.Y.C. has received travel sponsorship from Accuray and Varian MedicalSystems and grants from Varian Medical Systems, outside the submitted work. N.I.V. receives consulting fees from Sanofi, Regeneron, Oncocyte, and Eli Lilly and research funding from Mirati, outside the submitted work. J.Z. reports research funding from Merck, Johnson & Johnson, and Novartis and consultant fees from Bristol Myers Squibb (BMS), Johnson & Johnson, AstraZeneca, Geneplus, OrigMed, Novartis, and Innovent, outside the submitted work. J.V.H. serves on scientific advisory boards for AstraZeneca, Boehringer Ingelheim, Genentech, GSK, Eli Lilly, Novartis, Spectrum, EMD Serono, Sanofi, Takeda, Mirati Therapeutics, BMS, and Janssen Global Services; receives research support from AstraZeneca, Takeda, Boehringer Ingelheaim, and Spectrum; and receives licensing fees from Spectrum, all outside of the submitted work. The other authors declare no competing interests in the submitted work., (© 2023 The Author(s).)

The identification of biomarkers plays a crucial role in personalized medicine, both in the clinical and research settings. However, the contrast between predictive and prognostic biomarkers can be challenging due to the overlap between the two. A prognostic biomarker predicts the future outcome of cancer, regardless of treatment, and a predictive biomarker predicts the effectiveness of a therapeutic intervention. Misclassifying a prognostic biomarker as predictive (or vice versa) can have serious financial and personal consequences for patients. To address this issue, various statistical and machine learning approaches have been developed. The aim of this study is to present an in-depth analysis of recent advancements, trends, challenges, and future prospects in biomarker identification. A systematic search was conducted using PubMed to identify relevant studies published between 2017 and 2023. The selected studies were analyzed to better understand the concept of biomarker identification, evaluate machine learning methods, assess the level of research activity, and highlight the application of these methods in cancer research and treatment. Furthermore, existing obstacles and concerns are discussed to identify prospective research areas. We believe that this review will serve as a valuable resource for researchers, providing insights into the methods and approaches used in biomarker discovery and identifying future research opportunities.