An in silico approach helped to identify the best experimental design, population, and outcome for future randomized clinical trials

Artificial Intelligence and Anticancer Drug Development-Keep a Cool Head

Artificial intelligence (AI) is progressively spreading through the world of health, particularly in the field of oncology. AI offers new, exciting perspectives in drug development as toxicity and efficacy can be predicted from computer-designed active molecular structures. AI-based in silico clinical trials are still at their inception in oncology but their wider use is eagerly awaited as they should markedly reduce durations and costs. Health authorities cannot neglect this new paradigm in drug development and should take the requisite measures to include AI as a new pillar in conducting clinical research in oncology.

Generation of post-meal insulin correction boluses in type 1 diabetes simulation models for in-silico clinical trials: More realistic scenarios obtained using a decision tree approach

BACKGROUND AND OBJECTIVE

In type 1 diabetes (T1D) research, in-silico clinical trials (ISCTs) notably facilitate the design/testing of new therapies. Published simulation tools embed mathematical models of blood glucose (BG) and insulin dynamics, continuous glucose monitoring (CGM) sensors, and insulin treatments, but lack a realistic description of some aspects of patient lifestyle impacting on glucose control. Specifically, to effectively simulate insulin correction boluses, required to treat post-meal hyperglycemia (BG > 180 mg/dL), the timing of the bolus may be influenced by subjects' behavioral attitudes. In this work, we develop an easily interpretable model of the variability of correction bolus timing observed in real data, and embed it into a popular simulation tool for ISCTs.

METHODS

Using data collected in 196 adults with T1D monitored in free-living conditions, we trained a decision tree (DT) model to classify whether a correction bolus is injected in a future time window, based on predictors collected back in time, related to CGM data, previous insulin boluses and subject's characteristics. The performance was compared to that of a logistic regression classifier with LASSO regularization (LC), trained on the same dataset. After validation, the DT was embedded within a popular T1D simulation tool and an ISCT was performed to compare the simulated correction boluses against those observed in a subset of data not used for model training.

RESULTS

The DT provided better classification performance (accuracy: 0.792, sensitivity: 0.430, specificity: 0.878, precision: 0.455) than the LC and presented good interpretability. The most predictive features were related to CGM (and its temporal variations), time since the last insulin bolus, and time of the day. The correction boluses simulated by the DT, after implementation in the simulation tool, showed a good agreement with real-world data.

CONCLUSIONS

The DT developed in this work represents a simple set of rules to mimic the same timing of correction boluses observed on real data. The inclusion of the model in simulation tools allows investigators to perform ISCTs that more realistically represent the patient behavior in taking correction boluses and the post-prandial BG response. In the future, more complex models can be investigated.

Modeling the disruption of respiratory disease clinical trials by non-pharmaceutical COVID-19 interventions

Respiratory disease trials are profoundly affected by non-pharmaceutical interventions (NPIs) against COVID-19 because they perturb existing regular patterns of all seasonal viral epidemics. To address trial design with such uncertainty, we developed an epidemiological model of respiratory tract infection (RTI) coupled to a mechanistic description of viral RTI episodes. We explored the impact of reduced viral transmission (mimicking NPIs) using a virtual population and in silico trials for the bacterial lysate OM-85 as prophylaxis for RTI. Ratio-based efficacy metrics are only impacted under strict lockdown whereas absolute benefit already is with intermediate NPIs (eg. mask-wearing). Consequently, despite NPI, trials may meet their relative efficacy endpoints (provided recruitment hurdles can be overcome) but are difficult to assess with respect to clinical relevance. These results advocate to report a variety of metrics for benefit assessment, to use adaptive trial design and adapted statistical analyses. They also question eligibility criteria misaligned with the actual disease burden.

An artificial intelligence framework integrating longitudinal electronic health records with real-world data enables continuous pan-cancer prognostication

Despite widespread adoption of electronic health records (EHRs), most hospitals are not ready to implement data science research in the clinical pipelines. Here, we develop MEDomics, a continuously learning infrastructure through which multimodal health data are systematically organized and data quality is assessed with the goal of applying artificial intelligence for individual prognosis. Using this framework, currently composed of thousands of individuals with cancer and millions of data points over a decade of data recording, we demonstrate prognostic utility of this framework in oncology. As proof of concept, we report an analysis using this infrastructure, which identified the Framingham risk score to be robustly associated with mortality among individuals with early-stage and advanced-stage cancer, a potentially actionable finding from a real-world cohort of individuals with cancer. Finally, we show how natural language processing (NLP) of medical notes could be used to continuously update estimates of prognosis as a given individual's disease course unfolds.

The Future Role of Machine Learning in Clinical Transplantation

The use of artificial intelligence and machine learning (ML) has revolutionized our daily lives and will soon be instrumental in healthcare delivery. The rise of ML is due to multiple factors: increasing access to massive datasets, exponential increases in processing power, and key algorithmic developments that allow ML models to tackle increasingly challenging questions. Progressively more transplantation research is exploring the potential utility of ML models throughout the patient journey, although this has not yet widely transitioned into the clinical domain. In this review, we explore common approaches used in ML in solid organ clinical transplantation and consider opportunities for ML to help clinicians and patients. We discuss ways in which ML can aid leverage of large complex datasets, generate cutting-edge prediction models, perform clinical image analysis, discover novel markers in molecular data, and fuse datasets to generate novel insights in modern transplantation practice. We focus on key areas in transplantation in which ML is driving progress, explore the future potential roles of ML, and discuss the challenges and limitations of these powerful tools.

Mathematical Models of Meal Amount and Timing Variability With Implementation in the Type-1 Diabetes Patient Decision Simulator

BACKGROUND

In type 1 diabetes (T1D) research, in-silico clinical trials (ISCTs) have proven effective in accelerating the development of new therapies. However, published simulators lack a realistic description of some aspects of patient lifestyle which can remarkably affect glucose control. In this paper, we develop a mathematical description of meal carbohydrates (CHO) amount and timing, with the aim to improve the meal generation module in the T1D Patient Decision Simulator (T1D-PDS) published in Vettoretti et al.

METHODS

Data of 32 T1D subjects under free-living conditions for 4874 days were used. Univariate probability density function (PDF) parametric models with different candidate shapes were fitted, individually, against sample distributions of: CHO amounts of breakfast (CHOB), lunch (CHOL), dinner (CHOD), and snack (CHOS); breakfast timing (TB); and time between breakfast-lunch (TBL) and between lunch-dinner (TLD). Furthermore, a support vector machine (SVM) classifier was developed to predict the occurrence of a snack in future fixed-length time windows. Once embedded inside the T1D-PDS, an ISCT was performed.

RESULTS

Resulting PDF models were: gamma (CHOB, CHOS), lognormal (CHOL, TB), loglogistic (CHOD), and generalized-extreme-values (TBL, TLD). The SVM showed a classification accuracy of 0.8 over the test set. The distributions of simulated meal data were not statistically different from the distributions of the real data used to develop the models (α = 0.05).

CONCLUSIONS

The models of meal amount and timing variability developed are suitable for describing real data. Their inclusion in modules that describe patient behavior in the T1D-PDS can permit investigators to perform more realistic, reliable, and insightful ISCTs.

Combining Model-Based Clinical Trial Simulation, Pharmacoeconomics, and Value of Information to Optimize Trial Design

The Bayesian decision‐analytic approach to trial design uses prior distributions for treatment effects, updated with likelihoods for proposed trial data. Prior distributions for treatment effects based on previous trial results risks sample selection bias and difficulties when a proposed trial differs in terms of patient characteristics, medication adherence, or treatment doses and regimens. The aim of this study was to demonstrate the utility of using pharmacometric‐based clinical trial simulation (CTS) to generate prior distributions for use in Bayesian decision‐theoretic trial design. The methods consisted of four principal stages: a CTS to predict the distribution of treatment response for a range of trial designs; Bayesian updating for a proposed sample size; a pharmacoeconomic model to represent the perspective of a reimbursement authority in which price is contingent on trial outcome; and a model of the pharmaceutical company return on investment linking drug prices to sales revenue. We used a case study of febuxostat versus allopurinol for the treatment of hyperuricemia in patients with gout. Trial design scenarios studied included alternative treatment doses, inclusion criteria, input uncertainty, and sample size. Optimal trial sample sizes varied depending on the uncertainty of model inputs, trial inclusion criteria, and treatment doses. This interdisciplinary framework for trial design and sample size calculation may have value in supporting decisions during later phases of drug development and in identifying costly sources of uncertainty, and thus inform future research and development strategies.

A methodological framework for drug development in rare diseases. The CRESim program: Epilogue and perspectives

Based on the 'European Child-Rare-Euro-Simulation' (CRESim) project, this article proposes a generalizable strategy utilizing datasets analysis in combination with modeling and simulation, in order to optimize the clinical drug development applied in the field of rare diseases. The global process includes: (i) the simulation of a realistic virtual population of patients (modeled from a real dataset of patients), (ii) the modeling of disease pathophysiological components and of pharmacokinetic-pharmacodynamic relations of the drug(s) of interest, (iii) the modeling of several randomized controlled clinical trials (RCTs) designs and (iv) the analysis of the results (multi-dimensional approach for RCTs durations and precision of the estimation of the treatment effect). However, whereas modeling and numerical simulation may provide supplementary tools for drug development, they cannot be considered as a substitute for RCTs performed in 'real' patients.

Comparison of crossover and parallel-group designs for the identification of a binary predictive biomarker of the treatment effect

Pros and cons of crossover design are well known for estimating the treatment effect compared to parallel-group design, but remain unclear for identifying and estimating an interaction between a potential biomarker and the treatment effect. Such 'predictive' biomarkers, or 'effect modifiers', help to predict the response to specific treatments. The purpose of this report was to better characterize the advantages and disadvantages of crossover versus parallel-group design to identify predictive biomarkers. The treatment effect, the effect of a binary biomarker and their interaction were modelled using a linear model. The intra-subject correlation in the crossover design was taken into account through an intra-class correlation coefficient. The variance-covariance matrix of the parameters was derived and compared. For both trial designs, the variance of the parameter estimating an interaction between the treatment effect and a potential predictive biomarker corresponds to the variance of the parameter estimating the treatment effect, multiplied by the inverse of the frequency of the candidate biomarker. The ratio of the variance of the interaction parameter in the crossover to the variance estimated in the parallel-group design depends on the complement of the intra-class correlation coefficient. When planning a clinical trial including a search for candidate biomarker, the frequency of the candidate biomarker helps design the sample size, and the intra-subject correlation of the outcome should be taken into account for choosing between parallel-group and crossover designs.

Integrating molecular nuclear imaging in clinical research to improve anticancer therapy

Effective patient selection before or early during treatment is important to increasing the therapeutic benefits of anticancer treatments. This selection process is often predicated on biomarkers, predominantly biospecimen biomarkers derived from blood or tumour tissue; however, such biomarkers provide limited information about the true extent of disease or about the characteristics of different, potentially heterogeneous tumours present in an individual patient. Molecular imaging can also produce quantitative outputs; such imaging biomarkers can help to fill these knowledge gaps by providing complementary information on tumour characteristics, including heterogeneity and the microenvironment, as well as on pharmacokinetic parameters, drug-target engagement and responses to treatment. This integrative approach could therefore streamline biomarker and drug development, although a range of issues need to be overcome in order to enable a broader use of molecular imaging in clinical trials. In this Perspective article, we outline the multistage process of developing novel molecular imaging biomarkers. We discuss the challenges that have restricted the use of molecular imaging in clinical oncology research to date and outline future opportunities in this area.

Novel Deleterious nsSNPs within MEFV Gene that Could Be Used as Diagnostic Markers to Predict Hereditary Familial Mediterranean Fever: Using Bioinformatics Analysis

Background

Familial Mediterranean Fever (FMF) is the most common autoinflammatory disease (AID) affecting mainly the ethnic groups originating from Mediterranean basin. We aimed to identify the pathogenic SNPs in MEFV by computational analysis software.

Methods

We carried out in silico prediction of structural effect of each SNP using different bioinformatics tools to predict substitution influence on protein structure and function.

Result

23 novel mutations out of 857 nsSNPs are found to have deleterious effect on the MEFV structure and function.

Conclusion

This is the first in silico analysis of MEFV gene to prioritize SNPs for further genetic mapping studies. After using multiple bioinformatics tools to compare and rely on the results predicted, we found 23 novel mutations that may cause FMF disease and it could be used as diagnostic markers for Mediterranean basin populations.

Optimizing drug development in oncology by clinical trial simulation: Why and how?

In therapeutic research, the safety and efficacy of pharmaceutical products are necessarily tested on humans via clinical trials after an extensive and expensive preclinical development period. Methodologies such as computer modeling and clinical trial simulation (CTS) might represent a valuable option to reduce animal and human assays. The relevance of these methods is well recognized in pharmacokinetics and pharmacodynamics from the preclinical phase to postmarketing. However, they are barely used and are poorly regarded for drug approval, despite Food and Drug Administration and European Medicines Agency recommendations. The generalization of CTS could be greatly facilitated by the availability of software for modeling biological systems, by clinical trial studies and hospital databases. Data sharing and data merging raise legal, policy and technical issues that will need to be addressed. Development of future molecules will have to use CTS for faster development and thus enable better patient management. Drug activity modeling coupled with disease modeling, optimal use of medical data and increased computing speed should allow this leap forward. The realization of CTS requires not only bioinformatics tools to allow interconnection and global integration of all clinical data but also a universal legal framework to protect the privacy of every patient. While recognizing that CTS can never replace 'real-life' trials, they should be implemented in future drug development schemes to provide quantitative support for decision-making. This in silico medicine opens the way to the P4 medicine: predictive, preventive, personalized and participatory.

Using a meta-narrative literature review and focus groups with key stakeholders to identify perceived challenges and solutions for generating robust evidence on the effectiveness of treatments for rare diseases

INTRODUCTION

For many rare diseases, strong analytic study designs for evaluating the efficacy and effectiveness of interventions are challenging to implement because of small, geographically dispersed patient populations and underlying clinical heterogeneity. The objective of this study was to integrate perspectives from published literature and key rare disease stakeholders to better understand the perceived challenges and proposed methodological approaches to research on clinical interventions for rare diseases.

METHODS

We used a meta-narrative literature review and focus group interviews with key rare disease stakeholders to better understand the perceived challenges in generating and synthesizing treatment effectiveness evidence, and to describe various research methods for mitigating these identified challenges. Data from both components of this study were synthesized narratively according to research paradigms that emerged from our data.

RESULTS

Results from our meta-narrative literature review and focus group interviews revealed three fundamental challenges in generating robust treatment effectiveness evidence for rare diseases: i) limitations in recruiting a sufficient sample size to achieve planned statistical power; ii) inability to account for clinical heterogeneity and assess treatment effects across a clinical spectrum; and iii) reliance on short-term, surrogate outcomes whose clinical relevance is often unclear. We mapped these challenges and associated solutions to three interrelated research paradigms: i) explanatory evidence generation; ii) comparative effectiveness/pragmatic evidence generation; and iii) patient-oriented evidence generation. Within each research paradigm, numerous criticisms and potential solutions have been described with respect to overcoming these challenges from a research study design perspective.

CONCLUSIONS

Over time, discussions about clinical research for interventions for rare diseases have moved beyond methodological approaches to overcome challenges related to explanatory evidence generation, with increased recognition of the importance of pragmatic and patient-oriented evidence. Future directions for our work include developing a framework to expand current evidence synthesis practices to take into consideration many of the concepts discussed in this paper.

A systematic literature review of evidence-based clinical practice for rare diseases: what are the perceived and real barriers for improving the evidence and how can they be overcome?

BACKGROUND

Evidence-based clinical practice is challenging in all fields, but poses special barriers in the field of rare diseases. The present paper summarises the main barriers faced by clinical research in rare diseases, and highlights opportunities for improvement.

METHODS

Systematic literature searches without meta-analyses and internal European Clinical Research Infrastructure Network (ECRIN) communications during face-to-face meetings and telephone conferences from 2013 to 2017 within the context of the ECRIN Integrating Activity (ECRIN-IA) project.

RESULTS

Barriers specific to rare diseases comprise the difficulty to recruit participants because of rarity, scattering of patients, limited knowledge on natural history of diseases, difficulties to achieve accurate diagnosis and identify patients in health information systems, and difficulties choosing clinically relevant outcomes.

CONCLUSIONS

Evidence-based clinical practice for rare diseases should start by collecting clinical data in databases and registries; defining measurable patient-centred outcomes; and selecting appropriate study designs adapted to small study populations. Rare diseases constitute one of the most paradigmatic fields in which multi-stakeholder engagement, especially from patients, is needed for success. Clinical research infrastructures and expertise networks offer opportunities for establishing evidence-based clinical practice within rare diseases.

TFOS DEWS II Clinical Trial Design Report

The development of novel therapies for Dry Eye Disease (DED) is formidable, and relatively few treatments evaluated have been approved for marketing. In this report, the Subcommittee reviewed challenges in designing and conducting quality trials, with special reference to issues in trials in patients with DED and present the regulatory perspective on DED therapies. The Subcommittee reviewed the literature and while there are some observations about the possible reasons why so many trials have failed, there is no obvious single reason other than the lack of correlation between signs and symptoms in DED. Therefore the report advocates for conducting good quality studies, as described, going forward. A key recommendation for future studies is conduct consistent with Good Clinical Practice (GCP), including use of Good Manufacturing Practice (GMP) quality clinical trial material. The report also recommends that the design, treatments, and sample size be consistent with the investigational treatment, the objectives of the study, and the phase of development. Other recommendations for pivotal studies are a priori selection of the outcome measure, and an appropriate sample size.

In Silico Modeling of the Antiplatelet Pharmacodynamics of Low-dose Aspirin in Health and Disease

The influence of platelet turnover on cyclooxygenase (COX-1) inhibition by low-dose aspirin remains largely uncharacterized due to limited feasibility of studying aspirin pharmacodynamics in bone marrow precursors. We developed an in silico compartmental model describing the aspirin effects on COX-1 activity in a population of megakaryocytes (MK) and in peripheral platelets. Model parameters were inferred from the literature and calibrated using measurements of serum thromboxane B₂ (sTXB₂ ), as proxy of COX-1 activity in peripheral platelets, in 17 healthy subjects and 24 patients with essential thrombocythemia (ET). The model reproduced well the average time-course of sTXB₂ inhibition in healthy (accuracy = 10.4%), the reduced inhibition of sTXB₂ observed in ET, and the effect of different dosing regimens. In conclusion, the in silico model accurately describes COX-1 inactivation by low-dose aspirin in MK and platelets in different clinical settings, and might help personalize aspirin regimens in conditions of altered megakaryopoiesis.