Mathematical prediction of clinical outcomes in advanced cancer patients treated with checkpoint inhibitor immunotherapy

Virtual patient analysis identifies strategies to improve the performance of predictive biomarkers for PD-1 blockade

Patients with metastatic triple-negative breast cancer (TNBC) show variable responses to PD-1 inhibition. Efficient patient selection by predictive biomarkers would be desirable, but is hindered by the limited performance of existing biomarkers. Here, we leveraged in-silico patient cohorts generated using a quantitative systems pharmacology model of metastatic TNBC, informed by transcriptomic and clinical data, to explore potential ways to improve patient selection. We tested 90 biomarker candidates, including various cellular and molecular species, by a cutoff-based biomarker testing algorithm combined with machine learning-based feature selection. Combinations of pre-treatment biomarkers improved the specificity compared to single biomarkers at the cost of reduced sensitivity. On the other hand, early on-treatment biomarkers, such as the relative change in tumor diameter from baseline measured at two weeks after treatment initiation, achieved remarkably higher sensitivity and specificity. Further, blood-based biomarkers had a comparable ability to tumor- or lymph node-based biomarkers in identifying a subset of responders, potentially suggesting a less invasive way for patient selection.

Hybridizing mechanistic mathematical modeling with deep learning methods to predict individual cancer patient survival after immune checkpoint inhibitor therapy

We present a study where predictive mechanistic modeling is used in combination with deep learning methods to predict individual patient survival probabilities under immune checkpoint inhibitor (ICI) therapy. This hybrid approach enables prediction based on both measures that are calculable from mechanistic models (but may not be directly measurable in the clinic) and easily measurable quantities or characteristics (that are not always readily incorporated into predictive mechanistic models). The mechanistic model we have applied here can predict tumor response from CT or MRI imaging based on key mechanisms underlying checkpoint inhibitor therapy, and in the present work, its parameters were combined with readily-available clinical measures from 93 patients into a hybrid training set for a deep learning time-to-event predictive model. Analysis revealed that training an artificial neural network with both mechanistic modeling-derived and clinical measures achieved higher per-patient predictive accuracy based on event-time concordance, Brier score, and negative binomial log-likelihood-based criteria than when only mechanistic model-derived values or only clinical data were used. Feature importance analysis revealed that both clinical and model-derived parameters play prominent roles in neural network decision making, and in increasing prediction accuracy, further supporting the advantage of our hybrid approach. We anticipate that many existing mechanistic models may be hybridized with deep learning methods in a similar manner to improve predictive accuracy through addition of additional data that may not be readily implemented in mechanistic descriptions.

Potential of lncRNAs to regulate cuproptosis in hepatocellular carcinoma: Establishment and validation of a novel risk model

Cuproptosis, a distinct form of programmed cell death, is an emerging field in oncology with promising implications. This novel mode of cell death has the potential to become a regulatory target for tumor therapy, thus expanding the currently limited treatment options available for patients with cancer. Our research team focused on investigating the role of functional long non-coding RNA (lncRNAs) in hepatocellular carcinoma (HCC). We were particularly intrigued by the potential implications of HCC-lncRNAs on cuproptosis. Through a comprehensive analysis, we identified three cuproptosis-related lncRNAs (CRLs): AC018690.1, AL050341.2, and LINC02038. These lncRNAs were found to influence the sensitivity of HCC to cuproptosis. Based on our results, we constructed a risk model represented by the equation: risk score = 0.82 * AC018690.1 + 0.65 * AL050341.2 + 0.61 * LINC02038. Notably, significant disparities were observed in clinical features, such as the response rate to immunotherapy and targeted therapy, as well as in cellular characteristics, including the composition of the tumor immune microenvironment (TIME), when comparing the high- and low-risk groups. Most importantly, knockdown of these CRLs was confirmed to significantly weaken the resistance to cuproptosis in HCC. This effect resulted from the accelerated accumulation of lipoacylated-DLAT and lipoacylated-DLST. In summary, we identified three CRLs in HCC and established a novel risk model with potential clinical applications. Additionally, we proposed a potential therapeutic method consisting of sorafenib-copper ionophores-immunotherapy.

Deep reinforcement learning identifies personalized intermittent androgen deprivation therapy for prostate cancer

The evolution of drug resistance leads to treatment failure and tumor progression. Intermittent androgen deprivation therapy (IADT) helps responsive cancer cells compete with resistant cancer cells in intratumoral competition. However, conventional IADT is population-based, ignoring the heterogeneity of patients and cancer. Additionally, existing IADT relies on pre-determined thresholds of prostate-specific antigen to pause and resume treatment, which is not optimized for individual patients. To address these challenges, we framed a data-driven method in two steps. First, we developed a time-varied, mixed-effect and generative Lotka-Volterra (tM-GLV) model to account for the heterogeneity of the evolution mechanism and the pharmacokinetics of two ADT drugs Cyproterone acetate and Leuprolide acetate for individual patients. Then, we proposed a reinforcement-learning-enabled individualized IADT framework, namely, I$^{2}$ADT, to learn the patient-specific tumor dynamics and derive the optimal drug administration policy. Experiments with clinical trial data demonstrated that the proposed I$^{2}$ADT can significantly prolong the time to progression of prostate cancer patients with reduced cumulative drug dosage. We further validated the efficacy of the proposed methods with a recent pilot clinical trial data. Moreover, the adaptability of I$^{2}$ADT makes it a promising tool for other cancers with the availability of clinical data, where treatment regimens might need to be individualized based on patient characteristics and disease dynamics. Our research elucidates the application of deep reinforcement learning to identify personalized adaptive cancer therapy.

Investigating tumor-host response dynamics in preclinical immunotherapy experiments using a stepwise mathematical modeling strategy

Immunotherapies such as checkpoint blockade to PD1 and CTLA4 can have varied effects on individual tumors. To quantify the successes and failures of these therapeutics, we developed a stepwise mathematical modeling strategy and applied it to mouse models of colorectal and breast cancer that displayed a range of therapeutic responses. Using longitudinal tumor volume data, an exponential growth model was utilized to designate response groups for each tumor type. The exponential growth model was then extended to describe the dynamics of the quality of vasculature in the tumors via [18F] fluoromisonidazole (FMISO)-positron emission tomography (PET) data estimating tumor hypoxia over time. By calibrating the mathematical system to the PET data, several biological drivers of the observed deterioration of the vasculature were quantified. The mathematical model was then further expanded to explicitly include both the immune response and drug dosing, so that model simulations are able to systematically investigate biological hypotheses about immunotherapy failure and to generate experimentally testable predictions of immune response. The modeling results suggest elevated immune response fractions (> 30 %) in tumors unresponsive to immunotherapy is due to a functional immune response that wanes over time. This experimental-mathematical approach provides a means to evaluate dynamics of the system that could not have been explored using the data alone, including tumor aggressiveness, immune exhaustion, and immune cell functionality.

Advances in Radiotherapy Immune Modulation: From Bench-to-Bedside and Back Again

Pre-clinical and clinical data clearly demonstrate the immune modulatory effects of radiotherapy (RT) but clinical trials testing RT + immunotherapy have been equivocal. An improved understanding of the immune modulatory effects of RT and how practical parameters of RT delivery (site and number of lesions, dose, fractionation, timing) influence these effects are needed to optimally combine RT with immunotherapy. Additionally, increased exploration of immunotherapy combinations with RT, beyond immune checkpoint inhibitors, are needed. A "bench-to-bedside and back again" approach will improve our understanding of RT immune modulation and allow for the implementation of more effective RT + immunotherapy strategies.

In silico cancer immunotherapy trials uncover the consequences of therapy-specific response patterns for clinical trial design and outcome

Late-stage cancer immunotherapy trials often lead to unusual survival curve shapes, like delayed curve separation or a plateauing curve in the treatment arm. It is critical for trial success to anticipate such effects in advance and adjust the design accordingly. Here, we use in silico cancer immunotherapy trials - simulated trials based on three different mathematical models - to assemble virtual patient cohorts undergoing late-stage immunotherapy, chemotherapy, or combination therapies. We find that all three simulation models predict the distinctive survival curve shapes commonly associated with immunotherapies. Considering four aspects of clinical trial design - sample size, endpoint, randomization rate, and interim analyses - we demonstrate how, by simulating various possible scenarios, the robustness of trial design choices can be scrutinized, and possible pitfalls can be identified in advance. We provide readily usable, web-based implementations of our three trial simulation models to facilitate their use by biomedical researchers, doctors, and trialists.

A Biomathematical Model of Tumor Response to Radioimmunotherapy With αPDL1 and αCTLA4

There is evidence of synergy between radiotherapy and immunotherapy. Radiotherapy can increase liberation of tumor antigens, causing activation of antitumor T-cells. This effect can be boosted with immunotherapy. Radioimmunotherapy has potential to increase tumor control rates. Biomathematical models of response to radioimmunotherapy may help on understanding of the mechanisms affecting response, and assist clinicians on the design of optimal treatment strategies. In this work we present a biomathematical model of tumor response to radioimmunotherapy. The model uses the linear-quadratic response of tumor cells to radiation (or variation of it), and builds on previous developments to include the radiation-induced immune effect. We have focused this study on the combined effect of radiotherapy and αPDL1/ αCTLA4 therapies. The model can fit preclinical data of volume dynamics and control obtained with different dose fractionations and αPDL1/ αCTLA4. A biomathematical study of optimal combination strategies suggests that a good understanding of the involved biological delays, the biokinetics of the immunotherapy drug, and the interplay between them, may be of paramount importance to design optimal radioimmunotherapy schedules. Biomathematical models like the one we present can help to interpret experimental data on the synergy between radiotherapy and immunotherapy, and to assist in the design of more effective treatments.

Immune-checkpoint inhibitor therapy response evaluation using oncophysics-based mathematical models

The field of oncology has transformed with the advent of immunotherapies. The standard of care for multiple cancers now includes novel drugs that target key checkpoints that function to modulate immune responses, enabling the patient's immune system to elicit an effective anti-tumor response. While these immune-based approaches can have dramatic effects in terms of significantly reducing tumor burden and prolonging survival for patients, the therapeutic approach remains active only in a minority of patients and is often not durable. Multiple biological investigations have identified key markers that predict response to the most common form of immunotherapy-immune checkpoint inhibitors (ICI). These biomarkers help enrich patients for ICI but are not 100% predictive. Understanding the complex interactions of these biomarkers with other pathways and factors that lead to ICI resistance remains a major goal. Principles of oncophysics-the idea that cancer can be described as a multiscale physical aberration-have shown promise in recent years in terms of capturing the essence of the complexities of ICI interactions. Here, we review the biological knowledge of mechanisms of ICI action and how these are incorporated into modern oncophysics-based mathematical models. Building on the success of oncophysics-based mathematical models may help to discover new, rational methods to engineer immunotherapy for patients in the future. This article is categorized under: Therapeutic Approaches and Drug Discovery > Nanomedicine for Oncologic Disease.

SMoRe ParS: A novel methodology for bridging modeling modalities and experimental data applied to 3D vascular tumor growth

Multiscale systems biology is having an increasingly powerful impact on our understanding of the interconnected molecular, cellular, and microenvironmental drivers of tumor growth and the effects of novel drugs and drug combinations for cancer therapy. Agent-based models (ABMs) that treat cells as autonomous decision-makers, each with their own intrinsic characteristics, are a natural platform for capturing intratumoral heterogeneity. Agent-based models are also useful for integrating the multiple time and spatial scales associated with vascular tumor growth and response to treatment. Despite all their benefits, the computational costs of solving agent-based models escalate and become prohibitive when simulating millions of cells, making parameter exploration and model parameterization from experimental data very challenging. Moreover, such data are typically limited, coarse-grained and may lack any spatial resolution, compounding these challenges. We address these issues by developing a first-of-its-kind method that leverages explicitly formulated surrogate models (SMs) to bridge the current computational divide between agent-based models and experimental data. In our approach, Surrogate Modeling for Reconstructing Parameter Surfaces (SMoRe ParS), we quantify the uncertainty in the relationship between agent-based model inputs and surrogate model parameters, and between surrogate model parameters and experimental data. In this way, surrogate model parameters serve as intermediaries between agent-based model input and data, making it possible to use them for calibration and uncertainty quantification of agent-based model parameters that map directly onto an experimental data set. We illustrate the functionality and novelty of Surrogate Modeling for Reconstructing Parameter Surfaces by applying it to an agent-based model of 3D vascular tumor growth, and experimental data in the form of tumor volume time-courses. Our method is broadly applicable to situations where preserving underlying mechanistic information is of interest, and where computational complexity and sparse, noisy calibration data hinder model parameterization.

Mathematical modeling of cancer immunotherapy for personalized clinical translation

Encouraging advances are being made in cancer immunotherapy modeling, especially in the key areas of developing personalized treatment strategies based on individual patient parameters, predicting treatment outcomes and optimizing immunotherapy synergy when used in combination with other treatment approaches. Here we present a focused review of the most recent mathematical modeling work on cancer immunotherapy with a focus on clinical translatability. It can be seen that this field is transitioning from pure basic science to applications that can make impactful differences in patients' lives. We discuss how researchers are integrating experimental and clinical data to fully inform models so that they can be applied for clinical predictions, and present the challenges that remain to be overcome if widespread clinical adaptation is to be realized. Lastly, we discuss the most promising future applications and areas that are expected to be the focus of extensive upcoming modeling studies.

Protocol for mathematical prediction of patient response and survival to immune checkpoint inhibitor immunotherapy

This protocol describes the application of a mechanistic mathematical model of immune checkpoint inhibitor (ICI) immunotherapy to patient tumor imaging data for predicting solid tumor response and patient survival under ICI intervention. We describe steps for data collection and processing, data pipelines, and approaches to increase precision. The protocol is highly predictive as early as the first restaging after treatment start and can be used with standard-of-care imaging measures. For complete details on the use and execution of this protocol, please refer to Butner et al. (2020)¹ and Butner et al. (2021).².

Nivolumab serum concentration in metastatic melanoma patients could be related to outcome and enhanced immune activity: a gene profiling retrospective analysis

BACKGROUND

Nivolumab is an anti-PD-1 antibody approved for treating metastatic melanoma (MM), for which still limited evidence is available on the correlation between drug exposure and patient outcomes.

METHODS

In this observational retrospective study, we assessed whether nivolumab concentration is associated with treatment response in 88 patients with MM and if the patient's genetic profile plays a role in this association.

RESULTS

We observed a statistically significant correlation between nivolumab serum concentration and clinical outcomes, measured as overall and progression-free survival. Moreover, patients who achieved a clinical or partial response tended to have higher levels of nivolumab than those who reached stable disease or had disease progression. However, the difference was not statistically significant. In particular, patients who reached a clinical response had a significantly higher concentration of nivolumab and presented a distinct genetic signature, with more marked activation of ICOS and other genes involved in effector T-cells mediated proinflammatory pathways.

CONCLUSIONS

In conclusion, these preliminary results show that in patients with MM, nivolumab concentration correlates with clinical outcomes and is associated with an increased expression of ICOS and other genes involved in the activation of T effectors cells.

Modeling the effect of gut microbiome on therapeutic efficacy of immune checkpoint inhibitors against cancer

Immune checkpoint inhibitors have been shown to be highly successful against some solid metastatic malignancies, but only for a subset of patients who show durable clinical responses. The overall patient response rate is limited due to the interpatient heterogeneity. Preclinical and clinical studies have recently shown that the therapeutic responses can be improved through the modulation of gut microbiome. However, the underlying mechanisms are not fully understood. In this paper, we explored the effect of favorable and unfavorable gut bacteria on the therapeutic efficacy of anti-PD-1 against cancer by modeling the tumor-immune-gut microbiome interactions, and further examined the predictive markers of responders and non-responders to anti-PD-1. The dynamics of the gut bacteria was fitted to the clinical data of melanoma patients, and virtual patients data were generated based on the clinical patient survival data. Our simulation results show that low initial growth rate and low level of favorable bacteria at the initiation of anti-PD-1 therapy are predictive of non-responders, while high level of favorable bacteria at the initiation of anti-PD-1 therapy is predictive of responders. Simulation results also confirmed that it is possible to promote patients' response rate to anti-PD-1 by manipulating the gut bacteria composition of non-responders, whereby achieving long-term progression-free survival.

Mathematical Modeling to Simulate the Effect of Adding Radiation Therapy to Immunotherapy and Application to Hepatocellular Carcinoma

PURPOSE

To develop a comprehensive framework to simulate the response to immune checkpoint inhibitors (ICIs) in combination with radiation therapy (RT) and to apply the framework for investigating ICI-RT combination regimen in patients with hepatocellular carcinoma (HCC).

METHODS AND MATERIALS

The mechanistic mathematical model is based on dynamic biological interactions between the immune system and the tumor using input data from patient blood samples and outcomes of clinical trials. The cell compartments are described by ordinary differential equations and represent irradiated and nonirradiated tumor cells and lymphocytes. The effect of ICI is modeled using an immune activation term that is based on tumor size changes observed in a phase 1/2 clinical trial for HCC. Simulated combination regimen are based on ongoing ICI-RT trials.

RESULTS

The proposed framework successfully describes tumor volume trajectories observed in early-stage clinical trials of durvalumab monotherapy in patients with HCC. For ICI-RT treatment regimen the irradiated tumor fraction is the most important parameter for the efficacy. For 90% of the tumor cells being irradiated, adding RT to ICI yields an increase in clinical benefit from 33% to 71% in nonirradiated tumor sites. The model agrees with clinical data showing an association of outcome with initial tumor volume and lymphocyte counts. We demonstrate model application in clinical trial design to predict progression-free survival curves, showing that the cohort size to show significant improvement heavily depends on the irradiated tumor fraction.

CONCLUSIONS

We present a framework extending radiation cell kill models to include circulating lymphocytes and the effect of ICIs and enable simulation of combination strategies. The simulations predict that a significant amount of the benefit from RT in combination with ICI stems from the reduction in irradiated tumor burden and associated immune suppression. This aspect needs to be included in the interpretation of outcomes and the design of novel combination trials.

Thyroid cancer under the scope of emerging technologies

The vast majority of thyroid cancers originate from follicular cells. We outline outstanding issues at each step along the path of cancer patient care, from prevention to post-treatment follow-up and highlight how emerging technologies will help address them in the coming years. Three directions will dominate the coming technological landscape. Genomics will reveal tumoral evolutionary history and shed light on how these cancers arise from the normal epithelium and the genomics alteration driving their progression. Transcriptomics will gain cellular and spatial resolution providing a full account of intra-tumor heterogeneity and opening a window on the microenvironment supporting thyroid tumor growth. Artificial intelligence will set morphological analysis on an objective quantitative ground laying the foundations of a systematic thyroid tumor classification system. It will also integrate into unified representations the molecular and morphological perspectives on thyroid cancer.

A Pan-Cancer Analysis of Predictive Methylation Signatures of Response to Cancer Immunotherapy

Recently, tumor immunotherapy based on immune checkpoint inhibitors (ICI) has been introduced and widely adopted for various tumor types. Nevertheless, tumor immunotherapy has a few drawbacks, including significant uncertainty of outcome, the possibility of severe immune-related adverse events for patients receiving such treatments, and the lack of effective biomarkers to determine the ICI treatments' responsiveness. DNA methylation profiles were recently identified as an indicator of the tumor immune microenvironment. They serve as a potential hot spot for predicting responses to ICI treatment for their stability and convenience of measurement by liquid biopsy. We demonstrated the possibility of DNA methylation profiles as a predictor for responses to the ICI treatments at the pan-cancer level by analyzing DNA methylation profiles considered responsive and non-responsive to the treatments. An SVM model was built based on this differential analysis in the pan-cancer levels. The performance of the model was then assessed both at the pan-cancer level and in specific tumor types. It was also compared to the existing gene expression profile-based method. DNA methylation profiles were shown to be predictable for the responses to the ICI treatments in the TCGA cases in pan-cancer levels. The proposed SVM model was shown to have high performance in pan-cancer and specific cancer types. This performance was comparable to that of gene expression profile-based one. The combination of the two models had even higher performance, indicating the potential complementarity of the DNA methylation and gene expression profiles in the prediction of ICI treatment responses.

Early prediction of clinical response to checkpoint inhibitor therapy in human solid tumors through mathematical modeling

Background:

Checkpoint inhibitor therapy of cancer has led to markedly improved survival of a subset of patients in multiple solid malignant tumor types, yet the factors driving these clinical responses or lack thereof are not known. We have developed a mechanistic mathematical model for better understanding these factors and their relations in order to predict treatment outcome and optimize personal treatment strategies.

Methods:

Here, we present a translational mathematical model dependent on three key parameters for describing efficacy of checkpoint inhibitors in human cancer: tumor growth rate (α), tumor-immune infiltration (Λ), and immunotherapy-mediated amplification of anti-tumor response (µ). The model was calibrated by fitting it to a compiled clinical tumor response dataset (n = 189 patients) obtained from published anti-PD-1 and anti-PD-L1 clinical trials, and then validated on an additional validation cohort (n = 64 patients) obtained from our in-house clinical trials.

Results:

The derived parameters Λ and µ were both significantly different between responding versus nonresponding patients. Of note, our model appropriately classified response in 81.4% of patients by using only tumor volume measurements and within 2 months of treatment initiation in a retrospective analysis. The model reliably predicted clinical response to the PD-1/PD-L1 class of checkpoint inhibitors across multiple solid malignant tumor types. Comparison of model parameters to immunohistochemical measurement of PD-L1 and CD8+ T cells confirmed robust relationships between model parameters and their underlying biology.

Conclusions:

These results have demonstrated reliable methods to inform model parameters directly from biopsy samples, which are conveniently obtainable as early as the start of treatment. Together, these suggest that the model parameters may serve as early and robust biomarkers of the efficacy of checkpoint inhibitor therapy on an individualized per-patient basis.

Funding:

We gratefully acknowledge support from the Andrew Sabin Family Fellowship, Center for Radiation Oncology Research, Sheikh Ahmed Center for Pancreatic Cancer Research, GE Healthcare, Philips Healthcare, and institutional funds from the University of Texas M.D. Anderson Cancer Center. We have also received Cancer Center Support Grants from the National Cancer Institute (P30CA016672 to the University of Texas M.D. Anderson Cancer Center and P30CA072720 the Rutgers Cancer Institute of New Jersey). This research has also been supported in part by grants from the National Science Foundation Grant DMS-1930583 (ZW, VC), the National Institutes of Health (NIH) 1R01CA253865 (ZW, VC), 1U01CA196403 (ZW, VC), 1U01CA213759 (ZW, VC), 1R01CA226537 (ZW, RP, WA, VC), 1R01CA222007 (ZW, VC), U54CA210181 (ZW, VC), and the University of Texas System STARS Award (VC). BC acknowledges support through the SER Cymru II Programme, funded by the European Commission through the Horizon 2020 Marie Skłodowska-Curie Actions (MSCA) COFUND scheme and the Welsh European Funding Office (WEFO) under the European Regional Development Fund (ERDF). EK has also received support from the Project Purple, NIH (U54CA210181, U01CA200468, and U01CA196403), and the Pancreatic Cancer Action Network (16-65-SING). MF was supported through NIH/NCI center grant U54CA210181, R01CA222959, DoD Breast Cancer Research Breakthrough Level IV Award W81XWH-17-1-0389, and the Ernest Cockrell Jr. Presidential Distinguished Chair at Houston Methodist Research Institute. RP and WA received serial research awards from AngelWorks, the Gillson-Longenbaugh Foundation, and the Marcus Foundation. This work was also supported in part by grants from the National Cancer Institute to SHC (R01CA109322, R01CA127483, R01CA208703, and U54CA210181 CITO pilot grant) and to PYP (R01CA140243, R01CA188610, and U54CA210181 CITO pilot grant). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Current Landscape and Future Directions of Biomarkers for Immunotherapy in Hepatocellular Carcinoma

Hepatocellular carcinoma (HCC) is the most common liver cancer and one of the leading causes of cancer-related deaths in the world. Multiple immunotherapeutic approaches have been investigated to date, and immunotherapy has become the new standard of care therapy in HCC. However, the current role of immunotherapy in HCC remains non-curative. Given this context, a high priority for oncology is understanding the biomarkers that predict clinical response to immunotherapy, have the potential to improve patient selection to maximize the clinical benefit, and spare unnecessary toxicity. In this review, we summarize the key predictive and prognostic biomarkers investigated in immunotherapy clinical trials in HCC and the emerging biomarkers to serve as a roadmap for future clinical trials. Biomarkers from tumoral tissues including PDL-1 expression, tissue infiltrating lymphocytes, tumor mutational burden (TMB) and specific immune signatures, and from peripheral blood including neutrophil-to-lymphocytes ratio, platelet-to-lymphocytes ratio, circulating tumor DNA (ctDNA), circulating tumor cells (CTCs), and specific cytokines, along with gut microbiota are among the studied biomarkers to date in the HCC era. More integrative approaches, including mathematical biomarkers to predict immunotherapy outcomes, are yet to be studied in HCC.

The case for AI-driven cancer clinical trials - The efficacy arm in silico

Pharmaceutical agents in oncology currently have high attrition rates from early to late phase clinical trials. Recent advances in computational methods, notably causal artificial intelligence, and availability of rich clinico-genomic databases have made it possible to simulate the efficacy of cancer drug protocols in diverse patient populations, which could inform and improve clinical trial design. Here, we review the current and potential use of in silico trials and causal AI to increase the efficacy and safety of traditional clinical trials. We conclude that in silico trials using causal AI approaches can simulate control and efficacy arms, inform patient recruitment and regimen titrations, and better enable subgroup analyses critical for precision medicine.

Modelling treatment-response rates

The time course of tumour responses to immunotherapies can be mathematically predicted on the basis of tumour-growth rates, the rates of immune activation and of tumour–immune-cell interactions, and the efficacy of immune-mediated tumour killing.

Three-Dimensional Deep Noninvasive Radiomics for the Prediction of Disease Control in Patients With Metastatic Urothelial Carcinoma treated With Immunotherapy

INTRODUCTION

Immunotherapy is effective in a small percentage of patients with cancer and no reliable predictive biomarkers are currently available. Artificial Intelligence algorithms may automatically quantify radiologic characteristics associated with disease response to medical treatments.

METHODS

We investigated an innovative approach based on a 3-dimensional (3D) deep radiomics pipeline to classify visual features of chest-abdomen computed tomography (CT) scans with the aim of distinguishing disease control from progressive disease to immune checkpoint inhibitors (ICIs). Forty-two consecutive patients with metastatic urothelial cancer had progressed on first-line platinum-based chemotherapy and had baseline CT scans at immunotherapy initiation. The 3D-pipeline included self-learned visual features and a deep self-attention mechanism. According to the outcome to the ICIs, a 3D deep classifier semiautomatically categorized the most discriminative region of interest on the CT scans.

RESULTS

With a median follow-up of 13.3 months (95% CI, 11.1-15.6), the median overall survival was 8.5 months (95% CI, 3.1-13.8). According to disease response to immunotherapy, the median overall survival was 3.6 months (95% CI, 2.0-5.2) for patients with progressive disease; it was not yet reached for those with disease control. The predictive accuracy of the 3D-pipeline was 82.5% (sensitivity 96%; specificity, 60%). The addition of baseline clinical factors increased the accuracy to 92.5% by improving specificity to 87%; the accuracy of other architectures ranged from 72.5% to 90%.

CONCLUSION

Artificial Intelligence by 3D deep radiomics is a potential noninvasive biomarker for the prediction of disease control to ICIs in metastatic urothelial cancer and deserves validation in larger series.

Modeling Radioimmune Response-Current Status and Perspectives

The combination of immune therapy with radiation offers an exciting and promising treatment modality in cancer therapy. It has been hypothesized that radiation induces damage signals within the tumor, making it more detectable for the immune system. In combination with inhibiting immune checkpoints an effective anti-tumor immune response may be established. This inversion from tumor immune evasion raises numerous questions to be solved to support an effective clinical implementation: These include the optimum immune drug and radiation dose time courses, the amount of damage and associated doses required to stimulate an immune response, and the impact of lymphocyte status and dynamics. Biophysical modeling can offer unique insights, providing quantitative information addressing these factors and highlighting mechanisms of action. In this work we review the existing modeling approaches of combined ‘radioimmune’ response, as well as associated fields of study. We propose modeling attempts that appear relevant for an effective and predictive model. We emphasize the importance of the time course of drug and dose delivery in view to the time course of the triggered biological processes. Special attention is also paid to the dose distribution to circulating blood lymphocytes and the effect this has on immune competence.

A mathematical model for the quantification of a patient's sensitivity to checkpoint inhibitors and long-term tumour burden

A large proportion of patients with cancer are unresponsive to treatment with immune checkpoint blockade and other immunotherapies. Here, we report a mathematical model of the time-course of tumour responses to immune-checkpoint inhibitors. The model takes into account intrinsic tumour-growth rates, the rates of immune activation and of tumour–immune-cell interactions, and the efficacy of immune-mediated tumour killing. For 124 patients, four cancer types and two immunotherapy agents, the model reliably described the immune responses and final tumour burden across all different cancers and drug combinations examined. In validation cohorts from four clinical trials of checkpoint inhibitors (with a total of 177 patients), the model accurately stratified the patients according to reduced or increased long-term tumour burden. We also provide model-derived quantitative measures of treatment sensitivity for specific drug–cancer combinations. The model can be used to predict responses to therapy and to quantify specific drug–cancer sensitivities in individual patients.

The immune landscape of neuroblastoma: Challenges and opportunities for novel therapeutic strategies in pediatric oncology

Immunotherapy holds great promise for the treatment of pediatric cancers. In neuroblastoma, the recent implementation of anti-GD2 antibody Dinutuximab into the standard of care has improved patient outcomes substantially. However, 5-year survival rates are still below 50% in patients with high-risk neuroblastoma, which has sparked investigations into novel immunotherapeutic approaches. T cell-engaging therapies such as immune checkpoint blockade, antibody-mediated therapy and adoptive T cell therapy have proven remarkably successful in a range of adult cancers but still meet challenges in pediatric oncology. In neuroblastoma, their limited success may be due to several factors. Neuroblastoma displays low immunogenicity due to its low mutational load and lack of MHC-I expression. Tumour infiltration by T and NK cells is especially low in high-risk neuroblastoma and is prognostic for survival. Only a small fraction of tumour-infiltrating lymphocytes shows tumour reactivity. Moreover, neuroblastoma tumours employ a variety of immune evasion strategies, including expression of immune checkpoint molecules, induction of immunosuppressive myeloid and stromal cells, as well as secretion of immunoregulatory mediators, which reduce infiltration and reactivity of immune cells. Overcoming these challenges will be key to the successful implementation of novel immunotherapeutic interventions. Combining different immunotherapies, as well as personalised strategies, may be promising approaches. We will discuss the composition, function and prognostic value of tumour-infiltrating lymphocytes (TIL) in neuroblastoma, reflect on challenges for immunotherapy, including a lack of TIL reactivity and tumour immune evasion strategies, and highlight opportunities for immunotherapy and future perspectives with regard to state-of-the-art developments in the tumour immunology space.

Imaging-Based Subtypes of Pancreatic Ductal Adenocarcinoma Exhibit Differential Growth and Metabolic Patterns in the Pre-Diagnostic Period: Implications for Early Detection

BACKGROUND

Previously, we characterized subtypes of pancreatic ductal adenocarcinoma (PDAC) on computed-tomography (CT) scans, whereby conspicuous (high delta) PDAC tumors are more likely to have aggressive biology and poorer clinical outcomes compared to inconspicuous (low delta) tumors. Here, we hypothesized that these imaging-based subtypes would exhibit different growth-rates and distinctive metabolic effects in the period prior to PDAC diagnosis.

MATERIALS AND METHODS

Retrospectively, we evaluated 55 patients who developed PDAC as a second primary cancer and underwent serial pre-diagnostic (T0) and diagnostic (T1) CT-scans. We scored the PDAC tumors into high and low delta on T1 and, serially, obtained the biaxial measurements of the pancreatic lesions (T0-T1). We used the Gompertz-function to model the growth-kinetics and estimate the tumor growth-rate constant (α) which was used for tumor binary classification, followed by cross-validation of the classifier accuracy. We used maximum-likelihood estimation to estimate initiation-time from a single cell (10^-6 mm³) to a 10 mm³ tumor mass. Finally, we serially quantified the subcutaneous-abdominal-fat (SAF), visceral-abdominal-fat (VAF), and muscles volumes (cm³) on CT-scans, and recorded the change in blood glucose (BG) levels. T-test, likelihood-ratio, Cox proportional-hazards, and Kaplan-Meier were used for statistical analysis and p-value <0.05 was considered significant.

RESULTS

Compared to high delta tumors, low delta tumors had significantly slower average growth-rate constants (0.024 month^-1 vs. 0.088 month^-1, p<0.0001) and longer average initiation-times (14 years vs. 5 years, p<0.0001). α demonstrated high accuracy (area under the curve (AUC)=0.85) in classifying the tumors into high and low delta, with an optimal cut-off of 0.034 month^-1. Leave-one-out-cross-validation showed 80% accuracy in predicting the delta-class (AUC=0.84). High delta tumors exhibited accelerated SAF, VAF, and muscle wasting (p <0.001), and BG disturbance (p<0.01) compared to low delta tumors. Patients with low delta tumors had better PDAC-specific progression-free survival (log-rank, p<0.0001), earlier stage tumors (p=0.005), and higher likelihood to receive resection after PDAC diagnosis (p=0.008), compared to those with high delta tumors.

CONCLUSION

Imaging-based subtypes of PDAC exhibit distinct growth, metabolic, and clinical profiles during the pre-diagnostic period. Our results suggest that heterogeneous disease biology may be an important consideration in early detection strategies for PDAC.