Pharmacometric modeling and machine learning analyses of prognostic and predictive factors in the JAVELIN Gastric 100 phase III trial of avelumab

Longitudinal and time-to-event modeling for the survival of advanced pancreatic ductal adenocarcinoma patients

Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancers especially at advanced stage. In order to analyze the dynamics of potential prognostic biomarkers and further quantify their relationships with the overall survival (OS) of advanced PDAC patients, we herein developed a parametric time-to-event (TTE) model integrated with longitudinal submodels. Data from 104 patients receiving standard chemotherapies were retrospectively collected for model development, and other 54 patients were enrolled as external validation. The longitudinal submodels were developed with the time-course data of sum of longest diameters (SLD) of tumors, serum albumin (ALB) and body weight (BW) using nonlinear mixed effect models. The model-derived metrics including model parameters and individual predictions at different time points were further analyzed in the TTE model, together with other baseline information of patients. A linear growth-exponential shrinkage model was employed to describe the dynamics of SLD, while logistic models were used to fit the relationship of time prior to death with ALB and BW. The TTE model estimated the ALB and BW changes at the 9th week after chemotherapies as well as the baseline CA19-9 level that showed most significant impact on the OS, and the model-based simulations could provide individual survival rate predictions for patients with different prognostic factors. This study quantitatively demonstrates the importance of physical status and baseline disease for the OS of advanced PDAC patients, and highlights that timely nutrition support would be helpful to improve the prognosis.

Drug-induced torsadogenicity prediction model: An explainable machine learning-driven quantitative structure-toxicity relationship approach

Drug-induced Torsade de Pointes (TdP), a life-threatening polymorphic ventricular tachyarrhythmia, emerges due to the cardiotoxic effects of pharmaceuticals. The need for precise mechanisms and clinical biomarkers to detect this adverse effect presents substantial challenges in drug safety assessment. In this study, we propose that analyzing the physicochemical properties of pharmaceuticals can provide valuable insights into their potential for torsadogenic cardiotoxicity. Our research centers on estimating TdP risk based on the molecular structure of drugs. We introduce a novel quantitative structure-toxicity relationship (QSTR) prediction model that leverages an in silico approach developed by adopting the 4R rule in laboratory animals. This approach eliminates the need for animal testing, saves time, and reduces cost. Our algorithm has successfully predicted the torsadogenic risks of various pharmaceutical compounds. To develop this model, we employed Support Vector Machine (SVM) and ensemble techniques, including Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost). We enhanced the model's predictive accuracy through a rigorous two-step feature selection process. Furthermore, we utilized the SHapley Additive exPlanations (SHAP) technique to explain the prediction of torsadogenic risk, particularly within the RF model. This study represents a significant step towards creating a robust QSTR model, which can serve as an early screening tool for assessing the torsadogenic potential of pharmaceutical candidates or existing drugs. By incorporating molecular structure-based insights, we aim to enhance drug safety evaluation and minimize the risks of drug-induced TdP, ultimately benefiting both patients and the pharmaceutical industry.

Explainable machine learning prediction of edema adverse events in patients treated with tepotinib

Tepotinib is approved for the treatment of patients with non-small-cell lung cancer harboring MET exon 14 skipping alterations. While edema is the most prevalent adverse event (AE) and a known class effect of MET inhibitors including tepotinib, there is still limited understanding about the factors contributing to its occurrence. Herein, we apply machine learning (ML)-based approaches to predict the likelihood of occurrence of edema in patients undergoing tepotinib treatment, and to identify factors influencing its development over time. Data from 612 patients receiving tepotinib in five Phase I/II studies were modeled with two ML algorithms, Random Forest, and Gradient Boosting Trees, to predict edema AE incidence and severity. Probability calibration was applied to give a realistic estimation of the likelihood of edema AE. Best model was tested on follow-up data and on data from clinical studies unused while training. Results showed high performances across all the tested settings, with F1 scores up to 0.961 when retraining the model with the most relevant covariates. The use of ML explainability methods identified serum albumin as the most informative longitudinal covariate, and higher age as associated with higher probabilities of more severe edema. The developed methodological framework enables the use of ML algorithms for analyzing clinical safety data and exploiting longitudinal information through various covariate engineering approaches. Probability calibration ensures the accurate estimation of the likelihood of the AE occurrence, while explainability tools can identify factors contributing to model predictions, hence supporting population and individual patient-level interpretation.

Current Status and Future Directions: The Application of Artificial Intelligence/Machine Learning for Precision Medicine

Technological innovations, such as artificial intelligence (AI) and machine learning (ML), have the potential to expedite the goal of precision medicine, especially when combined with increased capacity for voluminous data from multiple sources and expanded therapeutic modalities; however, they also present several challenges. In this communication, we first discuss the goals of precision medicine, and contextualize the use of AI in precision medicine by showcasing innovative applications (e.g., prediction of tumor growth and overall survival, biomarker identification using biomedical images, and identification of patient population for clinical practice) which were presented during the February 2023 virtual public workshop entitled "Application of Artificial Intelligence and Machine Learning for Precision Medicine," hosted by the US Food and Drug Administration (FDA) and University of Maryland Center of Excellence in Regulatory Science and Innovation (M-CERSI). Next, we put forward challenges brought about by the multidisciplinary nature of AI, particularly highlighting the need for AI to be trustworthy. To address such challenges, we subsequently note practical approaches, viz., differential privacy, synthetic data generation, and federated learning. The proposed strategies - some of which are highlighted presentations from the workshop - are for the protection of personal information and intellectual property. In addition, methods such as the risk-based management approach and the need for an agile regulatory ecosystem are discussed. Finally, we lay out a call for action that includes sharing of data and algorithms, development of regulatory guidance documents, and pooling of expertise from a broad-spectrum of stakeholders to enhance the application of AI in precision medicine.

Machine Learning in Modeling Disease Trajectory and Treatment Outcomes: An Emerging Enabler for Model-Informed Precision Medicine

The increasing breadth and depth of resolution in biological and clinical data, including -omics and real-world data, requires advanced analytical techniques like artificial intelligence (AI) and machine learning (ML) to fully appreciate the impact of multi-dimensional population variability in intrinsic and extrinsic factors on disease progression and treatment outcomes. Integration of advanced data analytics in Quantitative Pharmacology is crucial for drug-disease knowledge management, enabling precise, efficient and inclusive drug development and utilization - an application we refer to as model-informed precision medicine. AI/ML enables characterization of the molecular and clinical sources of heterogeneity in disease trajectory, advancing end point qualification and biomarker discovery, and informing patient enrichment for proof-of-concept studies as well as trial designs for efficient evidence generation incorporating digital twins and virtual control arms. Explainable ML methods are valuable in elucidating predictors of efficacy and safety of pharmacological treatments, thereby informing response monitoring and risk mitigation strategies. In oncology, emerging opportunities exist for development of the next generation of disease models via ML-assisted joint longitudinal modeling of high-dimensional biomarker data such as circulating tumor DNA and radiomics profiles as predictors of survival outcomes. Finally, mining real-world data leveraging ML algorithms enables understanding of the impact of exclusion criteria on clinical outcomes, thereby informing rational design of appropriately inclusive clinical trials through data-driven broadening of eligibility criteria. Herein, we provide an overview of the aforementioned contexts of use of ML in drug-disease modeling based on examples across multiple therapeutic areas including neurology, rare diseases, autoimmune diseases, oncology and immuno-oncology.

Artificial Intelligence for Quantitative Modeling in Drug Discovery and Development: An Innovation and Quality Consortium Perspective on Use Cases and Best Practices

Recent breakthroughs in artificial intelligence (AI) and machine learning (ML) have ushered in a new era of possibilities across various scientific domains. One area where these advancements hold significant promise is model-informed drug discovery and development (MID3). To foster a wider adoption and acceptance of these advanced algorithms, the Innovation and Quality (IQ) Consortium initiated the AI/ML working group in 2021 with the aim of promoting their acceptance among the broader scientific community as well as by regulatory agencies. By drawing insights from workshops organized by the working group and attended by key stakeholders across the biopharma industry, academia, and regulatory agencies, this white paper provides a perspective from the IQ Consortium. The range of applications covered in this white paper encompass the following thematic topics: (i) AI/ML-enabled Analytics for Pharmacometrics and Quantitative Systems Pharmacology (QSP) Workflows; (ii) Explainable Artificial Intelligence and its Applications in Disease Progression Modeling; (iii) Natural Language Processing (NLP) in Quantitative Pharmacology Modeling; and (iv) AI/ML Utilization in Drug Discovery. Additionally, the paper offers a set of best practices to ensure an effective and responsible use of AI, including considering the context of use, explainability and generalizability of models, and having human-in-the-loop. We believe that embracing the transformative power of AI in quantitative modeling while adopting a set of good practices can unlock new opportunities for innovation, increase efficiency, and ultimately bring benefits to patients.

Tumor growth inhibition modeling in patients with second line biliary tract cancer and first line non-small cell lung cancer based on bintrafusp alfa trials

This analysis aimed to quantify tumor dynamics in patients receiving either bintrafusp alfa (BA) or pembrolizumab, by population pharmacokinetic (PK)-pharmacodynamic modeling, and investigate clinical and molecular covariates describing the variability in tumor dynamics by pharmacometric and machine-learning (ML) approaches. Data originated from two clinical trials in patients with biliary tract cancer (BTC; NCT03833661) receiving BA and non-small cell lung cancer (NSCLC; NCT03631706) receiving BA or pembrolizumab. Individual drug exposure was estimated from previously developed population PK models. Population tumor dynamics models were developed for each drug-indication combination, and covariate evaluations performed using nonlinear mixed-effects modeling (NLME) and ML (elastic net and random forest models) approaches. The three tumor dynamics' model structures all included linear tumor growth components and exponential tumor shrinkage. The final BTC model included the effect of drug exposure (area under the curve) and several covariates (demographics, disease-related, and genetic mutations). Drug exposure was not significant in either of the NSCLC models, which included two, disease-related, covariates in the BA arm, and none in the pembrolizumab arm. The covariates identified by univariable NLME and ML highly overlapped in BTC but showed less agreement in NSCLC analyses. Hyperprogression could be identified by higher tumor growth and lower tumor kill rates and could not be related to BA exposure. Tumor size over time was quantitatively characterized in two tumor types and under two treatments. Factors potentially related to tumor dynamics were assessed using NLME and ML approaches; however, their net impact on tumor size was considered as not clinically relevant.

Model-based prediction of progression-free survival for combination therapies in oncology

Progression-free survival (PFS) is an important clinical metric for comparing and evaluating similar treatments for the same disease within oncology. After the completion of a clinical trial, a descriptive analysis of the patients' PFS is often performed post hoc using the Kaplan-Meier estimator. However, to perform predictions, more sophisticated quantitative methods are needed. Tumor growth inhibition models are commonly used to describe and predict the dynamics of preclinical and clinical tumor size data. Moreover, frameworks also exist for describing the probability of different types of events, such as tumor metastasis or patient dropout. Combining these two types of models into a so-called joint model enables model-based prediction of PFS. In this paper, we have constructed a joint model from clinical data comparing the efficacy of FOLFOX against FOLFOX + panitumumab in patients with metastatic colorectal cancer. The nonlinear mixed effects framework was used to quantify interindividual variability (IIV). The model describes tumor size and PFS data well, and showed good predictive capabilities using truncated as well as external data. A machine-learning guided analysis was performed to reduce unexplained IIV by incorporating patient covariates. The model-based approach illustrated in this paper could be useful to help design clinical trials or to determine new promising drug candidates for combination therapy trials.

Modeling tumor size dynamics based on real-world electronic health records and image data in advanced melanoma patients receiving immunotherapy

The development of immune checkpoint inhibitors (ICIs) has revolutionized cancer therapy but only a fraction of patients benefits from this therapy. Model-informed drug development can be used to assess prognostic and predictive clinical factors or biomarkers associated with treatment response. Most pharmacometric models have thus far been developed using data from randomized clinical trials, and further studies are needed to translate their findings into the real-world setting. We developed a tumor growth inhibition model based on real-world clinical and imaging data in a population of 91 advanced melanoma patients receiving ICIs (i.e., ipilimumab, nivolumab, and pembrolizumab). Drug effect was modeled as an ON/OFF treatment effect, with a tumor killing rate constant identical for the three drugs. Significant and clinically relevant covariate effects of albumin, neutrophil to lymphocyte ratio, and Eastern Cooperative Oncology Group (ECOG) performance status were identified on the baseline tumor volume parameter, as well as NRAS mutation on tumor growth rate constant using standard pharmacometric approaches. In a population subgroup (n = 38), we had the opportunity to conduct an exploratory analysis of image-based covariates (i.e., radiomics features), by combining machine learning and conventional pharmacometric covariate selection approaches. Overall, we demonstrated an innovative pipeline for longitudinal analyses of clinical and imaging RWD with a high-dimensional covariate selection method that enabled the identification of factors associated with tumor dynamics. This study also provides a proof of concept for using radiomics features as model covariates.

An AI Approach to Generating MIDD Assets Across the Drug Development Continuum

Model-informed drug development involves developing and applying exposure-based, biological, and statistical models derived from preclinical and clinical data sources to inform drug development and decision-making. Discrete models are generated from individual experiments resulting in a single model expression that is utilized to inform a single stage-gate decision. Other model types provide a more holistic view of disease biology and potentially disease progression depending on the appropriateness of the underlying data sources for that purpose. Despite this awareness, most data integration and model development approaches are still reliant on internal (within company) data stores and traditional structural model types. An AI/ML-based MIDD approach relies on more diverse data and is informed by past successes and failures including data outside a host company (external data sources) that may enhance predictive value and enhance data generated by the sponsor to reflect more informed and timely experimentation. The AI/ML methodology also provides a complementary approach to more traditional modeling efforts that support MIDD and thus yields greater fidelity in decision-making. Early pilot studies support this assessment but will require broader adoption and regulatory support for more evidence and refinement of this paradigm. An AI/ML-based approach to MIDD has the potential to transform regulatory science and the current drug development paradigm, optimize information value, and increase candidate and eventually product confidence with respect to safety and efficacy. We highlight early experiences with this approach using the AI compute platforms as representative examples of how MIDD can be facilitated with an AI/ML approach.

Predicting metastasis in gastric cancer patients: machine learning-based approaches

Gastric cancer (GC), with a 5-year survival rate of less than 40%, is known as the fourth principal reason of cancer-related mortality over the world. This study aims to develop predictive models using different machine learning (ML) classifiers based on both demographic and clinical variables to predict metastasis status of patients with GC. The data applied in this study including 733 of GC patients, divided into a train and test groups at a ratio of 8:2, diagnosed at Taleghani tertiary hospital. In order to predict metastasis in GC, ML-based algorithms, including Naive Bayes (NB), Random Forest (RF), Support Vector Machine (SVM), Neural Network (NN), Decision Tree (RT) and Logistic Regression (LR), with 5-fold cross validation were performed. To assess the model performance, F1 score, precision, sensitivity, specificity, area under the curve (AUC) of receiver operating characteristic (ROC) curve and precision-recall AUC (PR-AUC) were obtained. 262 (36%) experienced metastasis among 733 patients with GC. Although all models have optimal performance, the indices of SVM model seems to be more appropiate (training set: AUC: 0.94, Sensitivity: 0.94; testing set: AUC: 0.85, Sensitivity: 0.92). Then, NN has the higher AUC among ML approaches (training set: AUC: 0.98; testing set: AUC: 0.86). The RF of ML-based models, which determine size of tumor and age as two essential variables, is considered as the third efficient model, because of higher specificity and AUC (84% and 87%). Based on the demographic and clinical characteristics, ML approaches can predict the metastasis status in GC patients. According to AUC, sensitivity and specificity in both SVM and NN can be regarded as better algorithms among 6 applied ML-based methods.

Disease trajectory of SLE clinical endpoints and covariates affecting disease severity and probability of response: Analysis of pooled patient-level placebo (Standard-of-Care) data to enable model-informed drug development

Systemic lupus erythematosus (SLE) is an autoimmune disease affecting multiple organ systems. Many investigational agents have failed or shown only modest effects when added to standard of care (SoC) therapy in placebo-controlled trials, and only two therapies have been approved for SLE in the last 60 years. Clinical trial outcomes have shown discordance in drug effects between clinical endpoints. Herein, we characterized longitudinal disease activity in the SLE population and the sources of variability by developing a latent disease trajectory model for SLE component endpoints (Systemic Lupus Erythematosus Disease Activity Index [SLEDAI], Physician's Global Assessment [PGA], British Isles Lupus Assessment Group Index [BILAG]) and composite endpoints (Systemic Lupus Erythematosus Responder Index [SRI], BILAG-based Composite Lupus Assessment [BICLA], and Lupus Low Disease Activity State [LLDAS]) using patient-level historical SoC data from nine phase II and III studies. Across all endpoints, in predictions up to 52 weeks from the final disease trajectory model, the following baseline covariates were associated with a greater decrease in SLE disease activity and higher response to placebo + SoC: Hispanic ethnicity from Central/South America, absence of hypocomplementemia, recent SLE diagnosis, and high baseline disease activity score using SLEDAI and BILAG separately. No discernible differences were observed in the trajectory of response to placebo + SoC across different SoC medications (antimalarial and immunosuppressant such as mycophenolate, methotrexate, and azathioprine). Across all endpoints, disease trajectory showed no difference in Asian versus non-Asian patients, supporting Asia-inclusive global SLE drug development. These results describe the first population approach to support a model-informed drug development framework in SLE.

Machine learning-guided covariate selection for time-to-event models developed from a small sample of real-world patients receiving bevacizumab treatment

Therapeutic outcomes in patients with metastatic colorectal cancer (mCRC) receiving bevacizumab treatment are highly variable, and a reliable predictive factor is not available. Progression-free survival (PFS) and overall survival (OS) were recorded from an observational, prospective study after 5 years of follow-up, including 46 patients with mCRC receiving bevacizumab treatment. Three vascular endothelial growth factor (VEGF)-A and two intercellular adhesion molecule-1 genes polymorphisms, age, gender, weight, dosing scheme, and co-treatments were collected. Given the relatively small number of events (37 [80%] for the PFS and 26 [57%] for the OS), to study the effect of these covariates on PFS and OS, a covariate analysis was performed using statistical and supervised machine learning techniques, including Cox regression, penalized Cox regression techniques (least absolute shrinkage and selection operator [LASSO], ridge regression, and elastic net), survival trees, and survival forest. The predictive performance of each method was evaluated in bootstrapped samples, using prediction error curves and the area under the curve of the receiver operating characteristic. The LASSO penalized Cox-regression model showed the best overall performance. Nonlinear mixed effects (NLME) models were developed, and a conventional stepwise covariate search was performed. Then, covariates identified as important by the LASSO model were included in the base NLME models developed for PFS and OS, resulting in improved models as compared to those obtained with the stepwise covariate search. It was shown that having gene polymorphisms in VEGFA (rs699947 and rs1570360) and ICAM1 (rs1799969) are associated with a favorable clinical outcome in patients with mCRC receiving bevacizumab treatment.

A novel analytical framework for risk stratification of real-world data using machine learning: A small cell lung cancer study

In recent studies, small cell lung cancer (SCLC) treatment guidelines based on Veterans' Administration Lung Study Group limited/extensive disease staging and resulted in broad and inseparable prognostic subgroups. Evidence suggests that the eight versions of tumor, node, and metastasis (TNM) staging can play an important role to address this issue. The aim of the present study was to improve the detection of prognostic subgroups from a real-word data (RWD) cohort of patients and analyze their patterns using a development pipeline with thoracic oncologists and machine learning methods. The method detected subgroups of patients informing unsupervised learning (partition around medoids) including the impact of covariates on prognosis (Cox regression and random survival forest). An analysis was carried out using patients with SCLC (n = 636) with stage IIIA-IVB according to TNM classification. The analysis yielded k = 7 compacted and well-separated clusters of patients. Performance status (Eastern Cooperative Oncology Group-Performance Status), lactate dehydrogenase, spreading of metastasis, cancer stage, and CRP were the baselines that characterized the subgroups. The selected clustering method outperformed standard clustering techniques, which were not capable of detecting meaningful subgroups. From the analysis of cluster treatment decisions, we showed the potential of future RWD applications to understand disease, develop individualized therapies, and improve healthcare decision making.

Longitudinal and time-to-event modeling for prognostic implications of radical surgery in retroperitoneal sarcoma

Retroperitoneal sarcoma (RPS) is a rare malignancy which can be difficult to manage due to the variety of clinical behaviors. In this study, we aimed to develop a parametric modeling framework to quantify the relationship between postoperative dynamics of several biomarkers and overall/progression-free survival of RPS. One hundred seventy-four patients with RPS who received surgical resection with curative intent at the Peking University Cancer Hospital Sarcoma Center were retrospectively included. Potential prognostic factors were preliminarily identified. Longitudinal analyses of body mass index (BMI), serum total protein (TP), and white blood cells (WBCs) were performed using nonlinear mixed effects models. The impacts of time-varying and time-invariant predictors on survival were investigated by parametric time-to-event (TTE) models. The majority of patients experienced decline in BMI, recovery of TP, as well as transient elevation in WBC counts after surgery, which significantly correlated with survival. An indirect-response model incorporating surgery effect described the fluctuation in percentage BMI. The recovery of TP was captured by a modified Gompertz model, and a semimechanistic model was selected for WBCs. TTE models estimated that the daily cumulative average of predicted BMI and WBC, the seventh-day TP, as well as certain baseline variables, were significant predictors of survival. Model-based simulations were performed to examine the clinical significance of prognostic factors. The current work quantified the individual trajectories of prognostic biomarkers in response to surgery and predicted clinical outcomes, which would constitute an additional strategy for disease monitoring and intervention in postoperative RPS.