In silico clinical trials: concepts and early adoptions

An update on nonhuman primate usage for drug and vaccine evaluation against filoviruses

INTRODUCTION

Due to their faithful recapitulation of human disease, nonhuman primates (NHPs) are considered the gold standard for evaluating drugs against Ebolavirus and other filoviruses. The long-term goal is to reduce the reliance on NHPs with more ethical alternatives. In silico simulations and organoid models have the potential to revolutionize drug testing by providing accurate, human-based systems that mimic disease processes and drug responses without the ethical concerns associated with animal testing. However, as these emerging technologies are still in their developmental infancy, NHP models are presently needed for late-stage evaluation of filovirus vaccines and drugs, as they provide critical insights into the efficacy and safety of new medical countermeasures.

AREAS COVERED

In this review, the authors introduce available NHP models and examine the existing literature on drug discovery for all medically significant filoviruses in corresponding models.

EXPERT OPINION

A deliberate shift toward animal-free models is desired to align with the 3Rs of animal research. In the short term, the use of NHP models can be refined and reduced by enhancing replicability and publishing negative data. Replacement involves a gradual transition, beginning with the selection and optimization of better small animal models; advancing organoid systems, and using in silico models to accurately predict immunological outcomes.

The utility and impact of digital endpoints for improving breast cancer outcomes

INTRODUCTION

In breast cancer clinical trials utilizing digital endpoints, wearable sensors record participants' health information during activities of daily living.  These sensors are worn on the wrist or finger, placed as a skin patch or headband, or embedded on clothing. Data collected from wearable sensors form the basis of a digital endpoint, useful for determining effects of novel treatments on health outcomes, particularly quality-of-life outcomes.

AREAS COVERED

References for this article were selected from a PubMed search spanning from 1 January 2017,to 1 July 2024, using the terms 'wearable sensors,' 'digital endpoints,' 'virtualtrials,' 'breast cancer.'  Additional articles from the authors' personal collection of papers and reviewers suggestions were also used.

EXPERT OPINION

Digital endpoints must be validated as proper surrogate measures for healthcare outcomes, prior to their use in breast cancer trials.  Wearable sensors may introduce biases, such as 'missing not-at-random bias,' and perhaps even exacerbate disparities in healthcare outcomes if patients not comfortable with their use are excluded from clinical trials, or if the accuracy of sensors varies between racial and ethnic groups. Therefore, before embarking on trials with digital endpoints, validation studies are required, and limitations and risks of such trials need to be addressed.

GPT-4 as a biomedical simulator

BACKGROUND

Computational simulation of biological processes can be a valuable tool for accelerating biomedical research, but usually requires extensive domain knowledge and manual adaptation. Large language models (LLMs) such as GPT-4 have proven surprisingly successful for a wide range of tasks. This study provides proof-of-concept for the use of GPT-4 as a versatile simulator of biological systems.

METHODS

We introduce SimulateGPT, a proof-of-concept for knowledge-driven simulation across levels of biological organization through structured prompting of GPT-4. We benchmarked our approach against direct GPT-4 inference in blinded qualitative evaluations by domain experts in four scenarios and in two quantitative scenarios with experimental ground truth. The qualitative scenarios included mouse experiments with known outcomes and treatment decision support in sepsis. The quantitative scenarios included prediction of gene essentiality in cancer cells and progression-free survival in cancer patients.

RESULTS

In qualitative experiments, biomedical scientists rated SimulateGPT's predictions favorably over direct GPT-4 inference. In quantitative experiments, SimulateGPT substantially improved classification accuracy for predicting the essentiality of individual genes and increased correlation coefficients and precision in the regression task of predicting progression-free survival.

CONCLUSION

This proof-of-concept study suggests that LLMs may enable a new class of biomedical simulators. Such text-based simulations appear well suited for modeling and understanding complex living systems that are difficult to describe with physics-based first-principles simulations, but for which extensive knowledge is available as written text. Finally, we propose several directions for further development of LLM-based biomedical simulators, including augmentation through web search retrieval, integrated mathematical modeling, and fine-tuning on experimental data.

Biomedical Data Science, Artificial Intelligence, and Ethics: Navigating Challenges in the Face of Explosive Growth

Advances in biomedical data science and artificial intelligence (AI) are profoundly changing the landscape of healthcare. This article reviews the ethical issues that arise with the development of AI technologies, including threats to privacy, data security, consent, and justice, as they relate to donors of tissue and data. It also considers broader societal obligations, including the importance of assessing the unintended consequences of AI research in biomedicine. In addition, this article highlights the challenge of rapid AI development against the backdrop of disparate regulatory frameworks, calling for a global approach to address concerns around data misuse, unintended surveillance, and the equitable distribution of AI's benefits and burdens. Finally, a number of potential solutions to these ethical quandaries are offered. Namely, the merits of advocating for a collaborative, informed, and flexible regulatory approach that balances innovation with individual rights and public welfare, fostering a trustworthy AI-driven healthcare ecosystem, are discussed.

What public health challenges and unmet medical needs would benefit from interdisciplinary collaboration in the EU? A survey and multi-stakeholder debate

In the past decade, significant European calls for research proposals have supported translational collaborative research on non-communicable and infectious diseases within the biomedical life sciences by bringing together interdisciplinary and multinational consortia. This research has advanced our understanding of disease pathophysiology, marking considerable scientific progress. Yet, it is crucial to retrospectively evaluate these efforts' societal impact. Research proposals should be thoughtfully designed to ensure that the research findings can be effectively translated into actionable policies. In addition, the choice of scientific methods plays a pivotal role in shaping the societal impact of research discoveries. Understanding the factors responsible for current unmet public health issues and medical needs is crucial for crafting innovative strategies for research policy interventions. A multistakeholder survey and a roundtable helped identify potential needs for consideration in the EU research and policy agenda. Based on survey findings, mental health disorders, metabolic syndrome, cancer, antimicrobial resistance, environmental pollution, and cardiovascular diseases were considered the public health challenges deserving prioritisation. In addition, early diagnosis, primary prevention, the impact of environmental pollution on disease onset and personalised medicine approaches were the most selected unmet medical needs. Survey findings enabled the formulation of some research-policies interventions (RPIs), which were further discussed during a multistakeholder online roundtable. The discussion underscored recent EU-level activities aligned with the survey-derived RPIs and facilitated an exchange of perspectives on public health and biomedical research topics ripe for interdisciplinary collaboration and warranting attention within the EU's research and policy agenda. Actionable recommendations aimed at facilitating the translation of knowledge into transformative, science-based policies are also provided.

Computational modelling of cardiovascular pathophysiology to risk stratify commercial spaceflight

For more than 60 years, humans have travelled into space. Until now, the majority of astronauts have been professional, government agency astronauts selected, in part, for their superlative physical fitness and the absence of disease. Commercial spaceflight is now becoming accessible to members of the public, many of whom would previously have been excluded owing to unsatisfactory fitness or the presence of cardiorespiratory diseases. While data exist on the effects of gravitational and acceleration (G) forces on human physiology, data on the effects of the aerospace environment in unselected members of the public, and particularly in those with clinically significant pathology, are limited. Although short in duration, these high acceleration forces can potentially either impair the experience or, more seriously, pose a risk to health in some individuals. Rather than expose individuals with existing pathology to G forces to collect data, computational modelling might be useful to predict the nature and severity of cardiovascular diseases that are of sufficient risk to restrict access, require modification, or suggest further investigation or training before flight. In this Review, we explore state-of-the-art, zero-dimensional, compartmentalized models of human cardiovascular pathophysiology that can be used to simulate the effects of acceleration forces, homeostatic regulation and ventilation-perfusion matching, using data generated by long-arm centrifuge facilities of the US National Aeronautics and Space Administration and the European Space Agency to risk stratify individuals and help to improve safety in commercial suborbital spaceflight.

Advancing vaccine development against Opisthorchis viverrini: A synergistic integration of omics technologies and advanced computational tools

The liver fluke O. viverrini (Opisthorchis viverrini), a neglected tropical disease (NTD), endemic to the Great Mekong Subregion (GMS), mainly afflicts the northeastern region of Thailand. It is a leading cause of cholangiocarcinoma (CCA) in humans. Presently, the treatment modalities for opisthorchiasis incorporate the use of the antihelminthic drug praziquantel, the rapid occurrence of reinfection, and the looming threat of drug resistance highlight the urgent need for vaccine development. Recent advances in "omics" technologies have proven to be a powerful tool for such studies. Utilizing candidate proteins identified through proteomics and refined via immunoproteomics, reverse vaccinology (RV) offers promising prospects for designing vaccines targeting essential antibody responses to eliminate parasite. Machine learning-based computational tools can predict epitopes of candidate protein/antigens exhibiting high binding affinities for B cells, MHC classes I and II, indicating strong potential for triggering both humoral and cell-mediated immune responses. Subsequently, these vaccine designs can undergo population-specific testing and docking/dynamics studies to assess efficacy and synergistic immunogenicity. Hence, refining proteomics data through immunoinformatics and employing computational tools to generate antigen-specific targets for trials offers a targeted and efficient approach to vaccine development that applies to all domains of parasite infections. In this review, we delve into the strategic antigen selection process using omics modalities for the O. viverrini parasite and propose an innovative framework for vaccine design. We harness omics technologies to revolutionize vaccine development, promising accelerated discoveries and streamlined preclinical and clinical evaluations.

Identifying Bayesian optimal experiments for uncertain biochemical pathway models

Pharmacodynamic (PD) models are mathematical models of cellular reaction networks that include drug mechanisms of action. These models are useful for studying predictive therapeutic outcomes of novel drug therapies in silico. However, PD models are known to possess significant uncertainty with respect to constituent parameter data, leading to uncertainty in the model predictions. Furthermore, experimental data to calibrate these models is often limited or unavailable for novel pathways. In this study, we present a Bayesian optimal experimental design approach for improving PD model prediction accuracy. We then apply our method using simulated experimental data to account for uncertainty in hypothetical laboratory measurements. This leads to a probabilistic prediction of drug performance and a quantitative measure of which prospective laboratory experiment will optimally reduce prediction uncertainty in the PD model. The methods proposed here provide a way forward for uncertainty quantification and guided experimental design for models of novel biological pathways.

Toward Personalized Salbutamol Therapy: Validating Virtual Patient-Derived Population Pharmacokinetic Model with Real-World Data

Interindividual variability, influenced by patient-specific factors including age, weight, gender, race, and genetics, among others, contributes to variations in therapeutic response. Population pharmacokinetic (popPK) modeling is an essential tool for pinpointing measurable factors affecting dose-concentration relationships and tailoring dosage regimens to individual patients. Herein, we developed a popPK model for salbutamol, a short-acting β2-agonist (SABA) used in asthma treatment, to identify key patient characteristics that influence treatment response. To do so, synthetic data from physiologically-based pharmacokinetic (PBPK) models was employed, followed by an external validation using real patient data derived from an equivalent study. Thirty-two virtual patients were included in this study. A two-compartment model, with first-order absorption (no delay), and linear elimination best fitted our data, according to diagnostic plots and selection criteria. External validation demonstrated a strong agreement between individual predicted and observed values. The incorporation of covariates into the basic structural model identified a significant impact of age on clearance (Cl) and intercompartmental clearance (Q); gender on Cl and the constant rate of absorption (ka); race on Cl; and weight on Cl in the volume of distribution of the peripheral compartment (V2). This study addresses critical challenges in popPK modeling, particularly data scarcity, incompleteness, and homogeneity, in traditional clinical trials, by leveraging synthetic data from PBPK modeling. Significant associations between individual characteristics and salbutamol's PK parameters, here uncovered, highlight the importance of personalized therapeutic regimens for optimal treatment outcomes.

Unlocking the full potential of mesenchymal stromal cell therapy for osteoarthritis through machine learning-based in silico trials

Despite the potential of mesenchymal stromal cells (MSCs) in osteoarthritis (OA) treatment, the challenge lies in addressing their therapeutic inconsistency. Clinical trials revealed significantly varied therapeutic outcomes among patients receiving the same allogenic MSCs but different treatment regimens. Therefore, optimizing personalized treatment strategies is crucial to fully unlock MSCs' potential and enhance therapeutic consistency. We employed the XGBoost algorithm to train a self-collected database comprising 37 published clinical reports to create a model capable of predicting the probability of effective pain relief and Western Ontario and McMaster Universities (WOMAC) index improvement in OA patients undergoing MSC therapy. Leveraging this model, extensive in silico simulations were conducted to identify optimal personalized treatment strategies and ideal patient profiles. Our in silico trials predicted that the individually optimized MSC treatment strategies would substantially increase patients' chances of recovery compared to the strategies used in reported clinical trials, thereby potentially benefiting 78.1%, 47.8%, 94.4% and 36.4% of the patients with ineffective short-term pain relief, short-term WOMAC index improvement, long-term pain relief and long-term WOMAC index improvement, respectively. We further recommended guidelines on MSC number, concentration, and the patients' appropriate physical (body mass index, age, etc.) and disease states (Kellgren-Lawrence grade, etc.) for OA treatment. Additionally, we revealed the superior efficacy of MSC in providing short-term pain relief compared to platelet-rich plasma therapy for most OA patients. This study represents the pioneering effort to enhance the efficacy and consistency of MSC therapy through machine learning applied to clinical data. The in silico trial approach holds immense potential for diverse clinical applications.

Derivation and Validation of Thresholds Using Synthetic Data Methods for Single-Test Screening of Emergency Department Patients with Possible Acute Myocardial Infarction Using a Point-of-Care Troponin Assay

BACKGROUND

Single-sample (screening) rule-out of acute myocardial infarction (AMI) with troponin requires derivation of a single-test screening threshold. In data sets with small event numbers, the lowest one or two concentrations of myocardial infarction (MI) patients dictate the threshold. This is not optimal. We aimed to demonstrate a process incorporating both real and synthetic data for deriving such thresholds using a novel pre-production high-precision point-of-care assay.

METHODS

cTnI concentrations were measured from thawed plasma using the Troponin I Next (TnI-Nx) assay (i-STAT; Abbott) in adults on arrival to the emergency department with symptoms suggestive of AMI. The primary outcome was an AMI or cardiac death within 30 days. We used internal-external validation with synthetic data production based on clinical and demographic data, plus the measured TnI-Nx concentration, to derive and validate decision thresholds for TnI-Nx. The target low-risk threshold was a sensitivity of 99% and a high-risk threshold specificity of >95%.

RESULTS

In total, 1356 patients were included, of whom 191 (14.1%) had the primary outcome. A total of 500 synthetic data sets were constructed. The mean low-risk threshold was determined to be 5 ng/L. This categorized 38% (95% CI, 6%-68%) to low-risk with a sensitivity of 99.0% (95% CI, 98.6%-99.5%) and a negative predictive value of 99.4% (95% CI, 97.6%-99.8%). A similarly derived high-risk threshold of 25 ng/L had a specificity of 95.0% (95% CI, 94.8%-95.1%) and a positive predictive value of 74.8% (95% CI, 71.5%-78.0%).

CONCLUSIONS

With the TnI-Nx assay, we successfully demonstrated an approach using synthetic data generation to derive low-risk thresholds for safe and effective screening.

A quantitative systems pharmacology workflow toward optimal design and biomarker stratification of atopic dermatitis clinical trials

BACKGROUND

The development of atopic dermatitis (AD) drugs is challenged by many disease phenotypes and trial design options, which are hard to explore experimentally.

OBJECTIVE

We aimed to optimize AD trial design using simulations.

METHODS

We constructed a quantitative systems pharmacology model of AD and standard of care (SoC) treatments and generated a phenotypically diverse virtual population whose parameter distribution was derived from known relationships between AD biomarkers and disease severity and calibrated using disease severity evolution under SoC regimens.

RESULTS

We applied this workflow to the immunomodulator OM-85, currently being investigated for its potential use in AD, and calibrated the investigational treatment model with the efficacy profile of an existing trial (thereby enriching it with plausible marker levels and dynamics). We assessed the sensitivity of trial outcomes to trial protocol and found that for this particular example the choice of end point is more important than the choice of dosing regimen and patient selection by model-based responder enrichment could increase the expected effect size. A global sensitivity analysis revealed that only a limited subset of baseline biomarkers is needed to predict the drug response of the full virtual population.

CONCLUSIONS

This AD quantitative systems pharmacology workflow built around knowledge of marker-severity relationships as well as SoC efficacy can be tailored to specific development cases to optimize several trial protocol parameters and biomarker stratification and therefore has promise to become a powerful model-informed AD drug development and personalized medicine tool.

The Next Horizon of Drug Development: External Control Arms and Innovative Tools to Enrich Clinical Trial Data

Conducting clinical trials (CTs) has become increasingly costly and complex in terms of designing and operationalizing. These challenges exist in running CTs on novel therapies, particularly in oncology and rare diseases, where CTs increasingly target narrower patient groups. In this study, we describe external control arms (ECA) and other relevant tools, such as virtualization and decentralized clinical trials (DCTs), and the ability to follow the clinical trial subjects in the real world using tokenization. ECAs are typically constructed by identifying appropriate external sources of data, then by cleaning and standardizing it to create an analysis-ready data file, and finally, by matching subjects in the external data with the subjects in the CT of interest. In addition, ECA tools also include subject-level meta-analysis and simulated subjects' data for analyses. By implementing the recent advances in digital health technologies and devices, virtualization, and DCTs, realigning of CTs from site-centric designs to virtual, decentralized, and patient-centric designs can be done, which reduces the patient burden to participate in the CTs and encourages diversity. Tokenization technology allows linking the CT data with real-world data (RWD), creating more comprehensive and longitudinal outcome measures. These tools provide robust ways to enrich the CT data for informed decision-making, reduce the burden on subjects and costs of trial operations, and augment the insights gained for the CT data.

Alternatives of Animal Models for Biomedical Research: a Comprehensive Review of Modern Approaches

Biomedical research has long relied on animal models to unravel the intricacies of human physiology and pathology. However, concerns surrounding ethics, expenses, and inherent species differences have catalyzed the exploration of alternative avenues. The contemporary alternatives to traditional animal models in biomedical research delve into three main categories of alternative approaches: in vitro models, in vertebrate models, and in silico models. This unique approach to artificial intelligence and machine learning has been a keen interest to be used in different biomedical research. The main goal of this review is to serve as a guide to researchers seeking novel avenues for their investigations and underscores the importance of considering alternative models in the pursuit of scientific knowledge and medical breakthroughs, including showcasing the broad spectrum of modern approaches that are revolutionizing biomedical research and leading the way toward a more ethical, efficient, and innovative future. Models can insight into cellular processes, developmental biology, drug interaction, assessing toxicology, and understanding molecular mechanisms.

Unlocking the potential of synthetic patients for accelerating clinical trials: Results of the first GIMEMA experience on acute myeloid leukemia patients

Artificial Intelligence has the potential to reshape the landscape of clinical trials through innovative applications, with a notable advancement being the emergence of synthetic patient generation. This process involves simulating cohorts of virtual patients that can either replace or supplement real individuals within trial settings. By leveraging synthetic patients, it becomes possible to eliminate the need for obtaining patient consent and creating control groups that mimic patients in active treatment arms. This method not only streamlines trial processes, reducing time and costs but also fortifies the protection of sensitive participant data. Furthermore, integrating synthetic patients amplifies trial efficiency by expanding the sample size. These straightforward and cost-effective methods also enable the development of personalized subject-specific models, enabling predictions of patient responses to interventions. Synthetic data holds great promise for generating real-world evidence in clinical trials while upholding rigorous confidentiality standards throughout the process. Therefore, this study aims to demonstrate the applicability and performance of these methods in the context of onco-hematological research, breaking through the theoretical and practical barriers associated with the implementation of artificial intelligence in medical trials.

Predictive Modelling in pharmacokinetics: from in-silico simulations to personalized medicine

INTRODUCTION

Pharmacokinetic parameters assessment is a critical aspect of drug discovery and development, yet challenges persist due to limited training data. Despite advancements in machine learning and in-silico predictions, scarcity of data hampers accurate prediction of drug candidates' pharmacokinetic properties.

AREAS COVERED

The study highlights current developments in human pharmacokinetic prediction, talks about attempts to apply synthetic approaches for molecular design, and searches several databases, including Scopus, PubMed, Web of Science, and Google Scholar. The article stresses importance of rigorous analysis of machine learning model performance in assessing progress and explores molecular modeling (MM) techniques, descriptors, and mathematical approaches. Transitioning to clinical drug development, article highlights AI (Artificial Intelligence) based computer models optimizing trial design, patient selection, dosing strategies, and biomarker identification. In-silico models, including molecular interactomes and virtual patients, predict drug performance across diverse profiles, underlining the need to align model results with clinical studies for reliability. Specialized training for human specialists in navigating predictive models is deemed critical. Pharmacogenomics, integral to personalized medicine, utilizes predictive modeling to anticipate patient responses, contributing to more efficient healthcare system. Challenges in realizing potential of predictive modeling, including ethical considerations and data privacy concerns, are acknowledged.

EXPERT OPINION

AI models are crucial in drug development, optimizing trials, patient selection, dosing, and biomarker identification and hold promise for streamlining clinical investigations.

Regulatory Framework for Implantable Neurostimulation Devices: Comparison of Systems in the US and European Union

BACKGROUND

Implantable neurostimulation devices must be authorized before they are placed on the market. For this purpose, requirements, and processes for assessing their fulfillment, have been defined in different jurisdictions.

OBJECTIVE

In this study, we aimed to address differences between the US and European Union (EU) regulatory systems and their relationship to innovation.

MATERIALS AND METHODS

A literature review and analysis were conducted using legal texts and guidance documents.

RESULTS

The US system has one central body, the Food and Drug Administration, whereas the EU system has several bodies with different responsibilities. The devices themselves are divided into risk classes, which are based on the vulnerability of the human body. This risk class determines the intensity of the review by the market authorization body. In addition to the requirements for development, manufacture, and distribution, the device itself must meet technical and clinical requirements. Compliance with technical requirements is indicated by nonclinical laboratory studies. Proof of efficacy is provided by means of clinical investigations. Procedures are defined for reviewing these elements. Once the market authorization process has been completed, the devices can be placed on the market. In the postmarketing phase, the devices must continue to be monitored, and measures must be initiated, if necessary.

CONCLUSIONS

Both US and EU systems are intended to ensure that only safe and effective devices find their way to and remain on the market. The basic approaches of the two systems are comparable. In detail, however, there are differences in ways these goals are achieved.

A perfectly imperfect engine: Utilizing the digital twin paradigm in pulmonary hypertension

Pulmonary hypertension (PH) is a severe medical condition with a number of treatment options, the majority of which are introduced without consideration of the underlying mechanisms driving it within an individual and thus a lack of tailored approach to treatment. The one exception is a patient presenting with apparent pulmonary arterial hypertension and shown to have vaso-responsive disease, whose clinical course and prognosis is significantly improved by high dose calcium channel blockers. PH is however characterized by a relative abundance of available data from patient cohorts, ranging from molecular data characterizing gene and protein expression in different tissues to physiological data at the organ level and clinical information. Integrating available data with mechanistic information at the different scales into computational models suggests an approach to a more personalized treatment of the disease using model-based optimization of interventions for individual patients. That is, constructing digital twins of the disease, customized to a patient, promises to be a key technology for personalized medicine, with the aim of optimizing use of existing treatments and developing novel interventions, such as new drugs. This article presents a perspective on this approach in the context of a review of existing computational models for different aspects of the disease, and it lays out a roadmap for a path to realizing it.

Mechanistic insight of α-mangostin encapsulation in 2-hydroxypropyl-β-cyclodextrin for solubility enhancement

α-Mangostin is the most abundant compound contained in the mangostin (Garcinia mangostana L.) plant which have been developed and proven to have many promising pharmacological effects. However, the low water solubility of α-mangostin causes limitations in its development in clinical purpose. To increase the solubility of a compound, a method currently being developed is to make drug inclusion complexes using cyclodextrins. This research aimed to use in silico techniques namely molecular docking study and molecular dynamics simulation to explore the molecular mechanism and stability of the encapsulation of α-mangostin using cyclodextrins. Two types of cyclodextrins were used including β-cyclodextrin and 2-hydroxypropyl-β-cyclodextrin docked against α-mangostin. From the molecular docking results, it shows that the α-mangostin complex with 2-hydroxypropyl-β-cyclodextrin provides the lowest binding energy value of -7.99 Kcal/mol compared to β-cyclodextrin value of -6.14 Kcal/mol. The α-mangostin complex with 2-hydroxypropyl-β-cyclodextrin also showed good stability based on molecular dynamics simulation during 100 ns. From molecular motion, RDF, Rg, SASA, density, total energy analyzes, this complex shows increased solubility in water and provided good stability. This indicates that the encapsulation of α-mangostin with 2-hydroxypropyl-β-cyclodextrin can increase the solubility of the α-mangostin.Communicated by Ramaswamy H. Sarma.

In silico trial for the assessment of givinostat dose adjustment rules based on the management of key hematological parameters in polycythemia vera patients

Polycythemia vera (PV) is a chronic myeloproliferative neoplasm characterized by excessive levels of platelets (PLT), white blood cells (WBC), and hematocrit (HCT). Givinostat (ITF2357) is a potent histone-deacetylase inhibitor that showed a good safety/efficacy profile in PV patients during phase I/II studies. A phase III clinical trial had been planned and an adaptive dosing protocol had been proposed where givinostat dose is iteratively adjusted every 28 days (one cycle) based on PLT, WBC, and HCT. As support, a simulation platform to evaluate and refine the proposed givinostat dose adjustment rules was developed. A population pharmacokinetic/pharmacodynamic model predicting the givinostat effects on PLT, WBC, and HCT in PV patients was developed and integrated with a control algorithm implementing the adaptive dosing protocol. Ten in silico trials in ten virtual PV patient populations were simulated 500 times. Considering an eight-treatment cycle horizon, reducing/increasing the givinostat daily dose by 25 mg/day step resulted in a higher percentage of patients with a complete hematological response (CHR), that is, PLT ≤400 × 109 /L, WBC ≤10 × 109 /L, and HCT < 45% without phlebotomies in the last three cycles, and a lower percentage of patients with grade II toxicity events compared with 50 mg/day adjustment steps. After the eighth cycle, 85% of patients were predicted to receive a dose ≥100 mg/day and 40.90% (95% prediction interval = [34, 48.05]) to show a CHR. These results were confirmed at the end of 12th, 18th, and 24th cycles, showing a stability of the response between the eighth and 24th cycles.

Radiology AI Deployment and Assessment Rubric (RADAR) to bring value-based AI into radiological practice

OBJECTIVE

To provide a comprehensive framework for value assessment of artificial intelligence (AI) in radiology.

METHODS

This paper presents the RADAR framework, which has been adapted from Fryback and Thornbury's imaging efficacy framework to facilitate the valuation of radiology AI from conception to local implementation. Local efficacy has been newly introduced to underscore the importance of appraising an AI technology within its local environment. Furthermore, the RADAR framework is illustrated through a myriad of study designs that help assess value.

RESULTS

RADAR presents a seven-level hierarchy, providing radiologists, researchers, and policymakers with a structured approach to the comprehensive assessment of value in radiology AI. RADAR is designed to be dynamic and meet the different valuation needs throughout the AI's lifecycle. Initial phases like technical and diagnostic efficacy (RADAR-1 and RADAR-2) are assessed pre-clinical deployment via in silico clinical trials and cross-sectional studies. Subsequent stages, spanning from diagnostic thinking to patient outcome efficacy (RADAR-3 to RADAR-5), require clinical integration and are explored via randomized controlled trials and cohort studies. Cost-effectiveness efficacy (RADAR-6) takes a societal perspective on financial feasibility, addressed via health-economic evaluations. The final level, RADAR-7, determines how prior valuations translate locally, evaluated through budget impact analysis, multi-criteria decision analyses, and prospective monitoring.

CONCLUSION

The RADAR framework offers a comprehensive framework for valuing radiology AI. Its layered, hierarchical structure, combined with a focus on local relevance, aligns RADAR seamlessly with the principles of value-based radiology.

CRITICAL RELEVANCE STATEMENT

The RADAR framework advances artificial intelligence in radiology by delineating a much-needed framework for comprehensive valuation.

KEYPOINTS

• Radiology artificial intelligence lacks a comprehensive approach to value assessment. • The RADAR framework provides a dynamic, hierarchical method for thorough valuation of radiology AI. • RADAR advances clinical radiology by bridging the artificial intelligence implementation gap.

Development and use of machine learning algorithms in vaccine target selection

Computer-aided discovery of vaccine targets has become a cornerstone of rational vaccine design. In this article, I discuss how Machine Learning (ML) can inform and guide key computational steps in rational vaccine design concerned with the identification of B and T cell epitopes and correlates of protection. I provide examples of ML models, as well as types of data and predictions for which they are built. I argue that interpretable ML has the potential to improve the identification of immunogens also as a tool for scientific discovery, by helping elucidate the molecular processes underlying vaccine-induced immune responses. I outline the limitations and challenges in terms of data availability and method development that need to be addressed to bridge the gap between advances in ML predictions and their translational application to vaccine design.

Rapid on-site evaluation (ROSE) of image-guided FNA specimens improves subsequent core biopsy adequacy in clinical trial patients: The impact of preanalytical factors and its correlation with survival

BACKGROUND

Sufficient tumor collection has become of utmost importance in therapeutic experimental protocols. Rapid on-site evaluation (ROSE) ensures adequate sampling for quantification of biomarkers, molecular analyses, and other ancillary studies. The objectives of this study were to evaluate the role of ROSE in trial-associated fine-needle aspiration (FNA) and to analyze predictors of adequacy and cumulative survival from in-house FNA cases used in clinical trials.

METHODS

Clinical trial FNA biopsies performed at a large academic institution were analyzed over 10 months using a comprehensive chart review of the electronic medical records. SPSS version 28 was used for statistical analysis.

RESULTS

Three hundred twenty-five FNAs were collected for 57 clinical trials. In total, 225 individual patients had an average of 1.4 FNA procedures each as a result of a multidepartmental collaborative effort. ROSE was performed for all patients, and adequacy was evaluated by cytotechnologists. Seventy-eight percent of samples were considered adequate, 14% were considered less than optimal, and 8% were considered inadequate, with the latter two categories designated together as less than adequate. The imaging modalities were mainly ultrasound-guided (n = 267; 82%) and computed tomography-guided (n = 58; 18%). There was a statistically significant association between adequate sampling and ultrasound-guided biopsies (83%) compared with computed tomography-guided biopsies (59%; p < .01). The effect of body mass index (BMI) on mortality was also a significant finding. The authors observed a survival benefit in patients who had elevated BMIs (range, 25.0-34.9 kg/m2 ) compared with those who were underweight (BMI, <18.5 kg/m2 ) or class III obese (BMI, >35.0 kg/m2 ; p < .01). Therefore, the best predictors of adequacy and mortality were imaging modality and BMI, respectively.

CONCLUSIONS

Ultrasound-guided modalities are recommended for obtaining adequate FNA sampling for clinical trials. In addition, patients with cancer who had slightly elevated BMIs (25.0-34.0 kg/m2 ) had increased overall survival in this cohort.

In Silico Clinical Trials: Is It Possible?

Modeling and simulation (M&S), including in silico (clinical) trials, helps accelerate drug research and development and reduce costs and have coined the term "model-informed drug development (MIDD)." Data-driven, inferential approaches are now becoming increasingly complemented by emerging complex physiologically and knowledge-based disease (and drug) models, but differ in setup, bottlenecks, data requirements, and applications (also reminiscent of the different scientific communities they arose from). At the same time, and within the MIDD landscape, regulators and drug developers start to embrace in silico trials as a potential tool to refine, reduce, and ultimately replace clinical trials. Effectively, silos between the historically distinct modeling approaches start to break down. Widespread adoption of in silico trials still needs more collaboration between different stakeholders and established precedence use cases in key applications, which is currently impeded by a shattered collection of tools and practices. In order to address these key challenges, efforts to establish best practice workflows need to be undertaken and new collaborative M&S tools devised, and an attempt to provide a coherent set of solutions is provided in this chapter. First, a dedicated workflow for in silico clinical trial (development) life cycle is provided, which takes up general ideas from the systems biology and quantitative systems pharmacology space and which implements specific steps toward regulatory qualification. Then, key characteristics of an in silico trial software platform implementation are given on the example of jinkō.ai (nova's end-to-end in silico clinical trial platform). Considering these enabling scientific and technological advances, future applications of in silico trials to refine, reduce, and replace clinical research are indicated, ranging from synthetic control strategies and digital twins, which overall shows promise to begin a new era of more efficient drug development.

Generative artificial intelligence empowers digital twins in drug discovery and clinical trials

INTRODUCTION

The concept of Digital Twins (DTs) translated to drug development and clinical trials describes virtual representations of systems of various complexities, ranging from individual cells to entire humans, and enables in silico simulations and experiments. DTs increase the efficiency of drug discovery and development by digitalizing processes associated with high economic, ethical, or social burden. The impact is multifaceted: DT models sharpen disease understanding, support biomarker discovery and accelerate drug development, thus advancing precision medicine. One way to realize DTs is by generative artificial intelligence (AI), a cutting-edge technology that enables the creation of novel, realistic and complex data with desired properties.

AREAS COVERED

The authors provide a brief introduction to generative AI and describe how it facilitates the modeling of DTs. In addition, they compare existing implementations of generative AI for DTs in drug discovery and clinical trials. Finally, they discuss technical and regulatory challenges that should be addressed before DTs can transform drug discovery and clinical trials.

EXPERT OPINION

The current state of DTs in drug discovery and clinical trials does not exploit the entire power of generative AI yet and is limited to simulation of a small number of characteristics. Nonetheless, generative AI has the potential to transform the field by leveraging recent developments in deep learning and customizing models for the needs of scientists, physicians and patients.

A risk and credibility framework for in silico clinical trials of medical devices

BACKGROUND AND OBJECTIVE

The use of in silico clinical trials (ISCTs) to generate clinically-relevant data on new medical devices is an emerging area of regulatory research. Interest in ISCTs stems from recognized challenges in acquiring sufficient clinical data and the continued maturation of in silico technologies. There is currently no guidance in place for evaluating the credibility of ISCT applications. The objective of this work was to adapt an existing risk-based credibility framework specifically for ISCT applications, and demonstrate its utility on a contemporary case study.

METHODS

Expanding on guidance currently in place for assessing the risk of traditional modeling applications of medical devices and demonstrating model credibility through benchtop validation activities, a framework is proposed to (1) evaluate the model risk for ISCT applications based on the independent factors of scope, coverage, and severity, and (2) assess the credibility of clinical validation activities based on consideration of the clinical comparator, the validation model, the agreement between the two, and the applicability of the clinical validation activities to the ISCT application.

RESULTS

The resulting framework spans across the range of ISCT applications that may be envisioned, as well as the variety of clinical datasets that can be used to demonstrate model credibility. Credibility factors reflect the expected clinical variability in the validation comparator and validation model, the statistical power of the comparator, the rigor of agreement between the comparator and model in terms of both inputs and outputs, and the overall similarity of the device in the validation activities to the device within the intended ISCT. When applied to a high-risk case study, the framework reveals that planned clinical validation activities require additional rigor in order to achieve the credibility targets, enabling an assessment of the validation effort relative to the potential benefit prior to investing in the validation studies.

DISCUSSION

An objective and risk-based framework for establishing credibility requirements for ISCT applications is a critical step in advancing ISCT from theory to practice. The proposed framework enforces that appropriate validation of ISCT applications requires evidence that the intended clinical environment is accurately represented. The framework will contribute to reducing uncertainty amongst technical, clinical, and regulatory constituents on ISCT applications, and promote rational adoption.

COMMBINI: an experimentally-informed COmputational Model of Macrophage dynamics in the Bone INjury Immunoresponse

Bone fracture healing is a well-orchestrated but complex process that involves numerous regulations at different scales. This complexity becomes particularly evident during the inflammatory stage, as immune cells invade the healing region and trigger a cascade of signals to promote a favorable regenerative environment. Thus, the emergence of criticalities during this stage might hinder the rest of the process. Therefore, the investigation of the many interactions that regulate the inflammation has a primary importance on the exploration of the overall healing progression. In this context, an in silico model named COMMBINI (COmputational Model of Macrophage dynamics in the Bone INjury Immunoresponse) has been developed to investigate the mechano-biological interactions during the early inflammatory stage at the tissue, cellular and molecular levels. An agent-based model is employed to simulate the behavior of immune cells, inflammatory cytokines and fracture debris as well as their reciprocal multiscale biological interactions during the development of the early inflammation (up to 5 days post-injury). The strength of the computational approach is the capacity of the in silico model to simulate the overall healing process by taking into account the numerous hidden events that contribute to its success. To calibrate the model, we present an in silico immunofluorescence method that enables a direct comparison at the cellular level between the model output and experimental immunofluorescent images. The combination of sensitivity analysis and a Genetic Algorithm allows dynamic cooperation between these techniques, enabling faster identification of the most accurate parameter values, reducing the disparity between computer simulation and histological data. The sensitivity analysis showed a higher sensibility of the computer model to the macrophage recruitment ratio during the early inflammation and to proliferation in the late stage. Furthermore, the Genetic Algorithm highlighted an underestimation of macrophage proliferation by in vitro experiments. Further experiments were conducted using another externally fixated murine model, providing an independent validation dataset. The validated COMMBINI platform serves as a novel tool to deepen the understanding of the intricacies of the early bone regeneration phases. COMMBINI aims to contribute to designing novel treatment strategies in both the biological and mechanical domains.

Identifying the patient harms to include in an in silico clinical trial

BACKGROUND AND OBJECTIVE

Clinical trials represent a crucial step in the development and approval of medical devices. These trials involve evaluating the safety and efficacy of the device in a controlled setting with human subjects. However, traditional clinical trials can be expensive, time-consuming, and ethically challenging. Augmenting clinical trials with data from computer simulations, so called in silico clinical trials (ISCT), has the potential to address these challenges while satisfying regulatory requirements. However, determination of the patient harms in scope of an ISCT is necessary to ensure all harms are sufficiently addressed while maximizing the utility of the ISCT. This topic is currently lacking guidance. The objective of this work is to propose a general method to determine which patient harms should be included in an ISCT for a regulatory submission.

METHODS

The proposed method considers the risk associated with the harm, the impact of the device on the likelihood of occurrence of the harm and the technical feasibility of evaluating the harm via ISCT. Consideration of the risk associated with the harm provides maximum clinical impact of the ISCT, in terms of focusing on those failure modes which are most relevant to the patient population. Consideration of the impact of the device on a particular harm, and the technical feasibility of modeling a particular harm supports that the technical effort is devoted to a problem that (1) is relevant to the device in question, and (2) can be solved with contemporary modeling techniques.

RESULTS AND CONCLUSIONS

As a case study, the proposed method is applied to a total shoulder replacement humeral system. With this framework, it is hoped that a consistent approach to scoping an ISCT can be adopted, supporting investment in ISCT by the industry, enabling consistent review of the ISCT approach across device disciplines by regulators, and providing maximum impact of modeling technologies in support of devices to improve patient outcomes.

ReplayBG: A Digital Twin-Based Methodology to Identify a Personalized Model From Type 1 Diabetes Data and Simulate Glucose Concentrations to Assess Alternative Therapies

OBJECTIVE

Design and assessment of new therapies for type 1 diabetes (T1D) management can be greatly facilitated by in silico simulations. The ReplayBG simulation methodology here proposed allows "replaying" the scenario behind data already collected by simulating the glucose concentration obtained in response to alternative insulin/carbohydrate therapies and evaluate their efficacy leveraging the concept of digital twin.

METHODS

ReplayBG is based on two steps. First, a personalized model of glucose-insulin dynamics is identified using insulin, carbohydrate, and continuous glucose monitoring (CGM) data. Then, this model is used to simulate the glucose concentration that would have been obtained by "replaying" the same portion of data using a different therapy. The validity of the methodology was evaluated on 100 virtual subjects using the UVa/Padova T1D Simulator (T1DS). In particular, the glucose concentration traces simulated by ReplayBG are compared with those provided by T1DS in five different scenarios of insulin and carbohydrate treatment modifications. Furthermore, we compared ReplayBG with a state-of-the-art methodology for the scope. Finally, two case studies using real data are also presented.

RESULTS

ReplayBG simulates with high accuracy the effect of the considered insulin and carbohydrate treatment alterations, performing significantly better than state-of-art method in almost all considered situations.

CONCLUSION

ReplayBG proved to be a reliable and robust tool to retrospectively explore the effect of new treatments for T1D on the glucose dynamics. It is freely available as open source software at https://github.com/gcappon/replay-bg.

SIGNIFICANCE

ReplayBG offers a new approach to preliminary evaluate new therapies for T1D management before clinical trials.

Virtual patient with temporal evolution for mechanical ventilation trial studies: A stochastic model approach

BACKGROUND AND OBJECTIVE

Healthcare datasets are plagued by issues of data scarcity and class imbalance. Clinically validated virtual patient (VP) models can provide accurate in-silico representations of real patients and thus a means for synthetic data generation in hospital critical care settings. This research presents a realistic, time-varying mechanically ventilated respiratory failure VP profile synthesised using a stochastic model.

METHODS

A stochastic model was developed using respiratory elastance (Ers) data from two clinical cohorts and averaged over 30-minute time intervals. The stochastic model was used to generate future Ers data based on current Ers values with added normally distributed random noise. Self-validation of the VPs was performed via Monte Carlo simulation and retrospective Ers profile fitting. A stochastic VP cohort of temporal Ers evolution was synthesised and then compared to an independent retrospective patient cohort data in a virtual trial across several measured patient responses, where similarity of profiles validates the realism of stochastic model generated VP profiles.

RESULTS

A total of 120,000 3-hour VPs for pressure control (PC) and volume control (VC) ventilation modes are generated using stochastic simulation. Optimisation of the stochastic simulation process yields an ideal noise percentage of 5-10% and simulation iteration of 200,000 iterations, allowing the simulation of a realistic and diverse set of Ers profiles. Results of self-validation show the retrospective Ers profiles were able to be recreated accurately with a mean squared error of only 0.099 [0.009-0.790]% for the PC cohort and 0.051 [0.030-0.126]% for the VC cohort. A virtual trial demonstrates the ability of the stochastic VP cohort to capture Ers trends within and beyond the retrospective patient cohort providing cohort-level validation.

CONCLUSION

VPs capable of temporal evolution demonstrate feasibility for use in designing, developing, and optimising bedside MV guidance protocols through in-silico simulation and validation. Overall, the temporal VPs developed using stochastic simulation alleviate the need for lengthy, resource intensive, high cost clinical trials, while facilitating statistically robust virtual trials, ultimately leading to improved patient care and outcomes in mechanical ventilation.

Credibility assessment of computational models according to ASME V&V40: Application to the Bologna Biomechanical Computed Tomography solution

BACKGROUND AND OBJECTIVE

When a computational model aims to be adopted beyond research purposes, e.g. to inform a clinical or regulatory decision, trust must be placed in its predictive accuracy. This practically translates into the need to demonstrate its credibility. In fact, prior to its adoption for regulatory purposes, an in silico methodology should be proven credible enough for the scope. This has become especially relevant as, although evidence of the safety and efficacy of new medical products or interventions has been traditionally provided to the regulator experimentally, i.e., in vivo or ex vivo, recently the idea to inform a regulatory decision in silico has made its way in the regulatory scenario. While a harmonised technical standard is currently missing in the EU regulatory system, in 2018 the ASME issued V&V40-2018, where a risk-based framework to assess the credibility of a computational model through the performance of predefined credibility activities is provided. The credibility framework is here applied to Bologna Biomechanical Computed Tomography (BBCT) solution, which predicts the absolute risk of fracture at the femur for a subject. BBCT has recently been the object of a qualification advice request to the European Medicine Agency.

METHODS

The full implementation of ASME V&V40-2018 framework on BBCT is shown. Starting from BBCT proposed context of use the whole credibility plan is presented and the credibility activities (Verification, Validation, Applicability) described together with the achieved credibility levels.

RESULTS

BBCT risk is judged medium, and the credibility levels achieved considered acceptable. The uncertainties intrinsically present in the material properties assignment affected BBCT predictions to the highest extent.

CONCLUSIONS

This work provides the practical application of the ASME V&V40-2018 risk-based credibility assessment framework, which could be applied to demonstrate model credibility in any field and support future regulatory submissions and foster the adoption of In Silico Trials.

A Markov Model of Gap Occurrence in Continuous Glucose Monitoring Data for Realistic in Silico Clinical Trials

BACKGROUND AND OBJECTIVE

Continuous glucose monitoring (CGM) sensors measure interstitial glucose concentration every 1-5 min for days or weeks. New CGM-based diabetes therapies are often tested in in silico clinical trials (ISCTs) using diabetes simulators. Accurate models of CGM sensor inaccuracies and failures could help improve the realism of ISCTs. However, the modeling of CGM failures has not yet been fully addressed in the literature. This work aims to develop a mathematical model of CGM gaps, i.e., occasional portions of missing data generated by temporary sensor errors (e.g., excessive noise or artifacts).

METHODS

Two datasets containing CGM traces collected in 167 adults and 205 children, respectively, using the Dexcom G6 sensor (Dexcom Inc., San Diego, CA) were used. Four Markov models, of increasing complexity, were designed to describe three main characteristics: number of gaps for each sensor, gap distribution in the monitoring days, and gap duration. Each model was identified on a portion of each dataset (training set). The remaining portion of each dataset (real test set) was used to evaluate model performance through a Monte Carlo simulation approach. Each model was used to generate 100 simulated test sets with the same size as the real test set. The distributions of gap characteristics on the simulated test sets were compared with those observed on the real test set, using the two-sample Kolmogorov-Smirnov test and the Jensen-Shannon divergence.

RESULTS

A six-state Markov model, having two states to describe normal sensor operation and four states to describe gap occurrence, achieved the best results. For this model, the Kolmogorov-Smirnov test found no significant differences between the distribution of simulated and real gap characteristics. Moreover, this model obtained significantly lower Jensen-Shannon divergence values than the other models.

CONCLUSIONS

A Markov model describing CGM gaps was developed and validated on two real datasets. The model describes well the number of gaps for each sensor, the gap distribution over monitoring days, and the gap durations. Such a model can be integrated into existing diabetes simulators to realistically simulate CGM gaps in ISCTs and thus enable the development of more effective and robust diabetes management strategies.

A quantitative systems pharmacology model for certolizumab pegol treatment in moderate-to-severe psoriasis

Background

Psoriasis is a chronic immune-mediated inflammatory systemic disease with skin manifestations characterized by erythematous, scaly, itchy and/or painful plaques resulting from hyperproliferation of keratinocytes. Certolizumab pegol [CZP], a PEGylated antigen binding fragment of a humanized monoclonal antibody against TNF-alpha, is approved for the treatment of moderate-to-severe plaque psoriasis. Patients with psoriasis present clinical and molecular variability, affecting response to treatment. Herein, we utilized an in silico approach to model the effects of CZP in a virtual population (vPop) with moderate-to-severe psoriasis. Our proof-of-concept study aims to assess the performance of our model in generating a vPop and defining CZP response variability based on patient profiles.

Methods

We built a quantitative systems pharmacology (QSP) model of a clinical trial-like vPop with moderate-to-severe psoriasis treated with two dosing schemes of CZP (200 mg and 400 mg, both every two weeks for 16 weeks, starting with a loading dose of CZP 400 mg at weeks 0, 2, and 4). We applied different modelling approaches: (i) an algorithm to generate vPop according to reference population values and comorbidity frequencies in real-world populations; (ii) physiologically based pharmacokinetic (PBPK) models of CZP dosing schemes in each virtual patient; and (iii) systems biology-based models of the mechanism of action (MoA) of the drug.

Results

The combination of our different modelling approaches yielded a vPop distribution and a PBPK model that aligned with existing literature. Our systems biology and QSP models reproduced known biological and clinical activity, presenting outcomes correlating with clinical efficacy measures. We identified distinct clusters of virtual patients based on their psoriasis-related protein predicted activity when treated with CZP, which could help unravel differences in drug efficacy in diverse subpopulations. Moreover, our models revealed clusters of MoA solutions irrespective of the dosing regimen employed.

Conclusion

Our study provided patient specific QSP models that reproduced clinical and molecular efficacy features, supporting the use of computational methods as modelling strategy to explore drug response variability. This might shed light on the differences in drug efficacy in diverse subpopulations, especially useful in complex diseases such as psoriasis, through the generation of mechanistically based hypotheses.

The Coming of Age of AI/ML in Drug Discovery, Development, Clinical Testing, and Manufacturing: The FDA Perspectives

Artificial intelligence (AI) and machine learning (ML) represent significant advancements in computing, building on technologies that humanity has developed over millions of years-from the abacus to quantum computers. These tools have reached a pivotal moment in their development. In 2021 alone, the U.S. Food and Drug Administration (FDA) received over 100 product registration submissions that heavily relied on AI/ML for applications such as monitoring and improving human performance in compiling dossiers. To ensure the safe and effective use of AI/ML in drug discovery and manufacturing, the FDA and numerous other U.S. federal agencies have issued continuously updated, stringent guidelines. Intriguingly, these guidelines are often generated or updated with the aid of AI/ML tools themselves. The overarching goal is to expedite drug discovery, enhance the safety profiles of existing drugs, introduce novel treatment modalities, and improve manufacturing compliance and robustness. Recent FDA publications offer an encouraging outlook on the potential of these tools, emphasizing the need for their careful deployment. This has expanded market opportunities for retraining personnel handling these technologies and enabled innovative applications in emerging therapies such as gene editing, CRISPR-Cas9, CAR-T cells, mRNA-based treatments, and personalized medicine. In summary, the maturation of AI/ML technologies is a testament to human ingenuity. Far from being autonomous entities, these are tools created by and for humans designed to solve complex problems now and in the future. This paper aims to present the status of these technologies, along with examples of their present and future applications.

Translational Pharmacokinetic/Pharmacodynamic Modeling and Simulation of Oxaliplatin and Irinotecan in Colorectal Cancer

Despite the recent advances in this field, there are limited methods for translating organoid-based study results to clinical response. The goal of this study was to develop a pharmacokinetic/pharmacodynamic (PK/PD) model to facilitate the translation, using oxaliplatin and irinotecan treatments with colorectal cancer (CRC) as examples. The PK models were developed using qualified oxaliplatin and irinotecan PK data from the literature. The PD models were developed based on antitumor efficacy data of SN-38 and oxaliplatin evaluated in vitro using tumor organoids. To predict the clinical response, translational scaling of the models was established by incorporating predicted ultrafiltration platinum in plasma or SN-38 in tumors to PD models as the driver of efficacy. The final PK/PD model can predict PK profiles and responses following treatments with oxaliplatin or irinotecan. After generation of virtual patient cohorts, this model simulated their tumor shrinkages following treatments, which were used in analyzing the efficacies of the two treatments. Consistent with the published clinical trials, the model simulation suggested similar patient responses following the treatments of oxaliplatin and irinotecan with regards to the probabilities of progression-free survival (HR = 1.05, 95%CI [0.97;1.15]) and the objective response rate (OR = 1.15, 95%CI [1.00;1.32]). This proposed translational PK/PD modeling approach provides a significant tool for predicting clinical responses of different agents, which may help decision-making in drug development and guide clinical trial design.

Epistemic Rights and Responsibilities of Digital Simulacra for Biomedicine

Big data and AI have enabled digital simulation for prediction of future health states or behaviors of specific individuals, populations or humans in general. "Digital simulacra" use multimodal datasets to develop computational models that are virtual representations of people or groups, generating predictions of how systems evolve and react to interventions over time. These include digital twins and virtual patients for in silico clinical trials, both of which seek to transform research and health care by speeding innovation and bridging the epistemic gap between population-based research findings and their application to the individual. Nevertheless, digital simulacra mark a major milestone on a trajectory to embrace the epistemic culture of data science and a potential abandonment of medical epistemological concepts of causality and representation. In doing so, "data first" approaches potentially shift moral attention from actual patients and principles, such as equity, to simulated patients and patient data.

Synthetic biomedical data generation in support of In Silico Clinical Trials

Living in the era of Big Data, one may advocate that the additional synthetic generation of data is redundant. However, to be able to truly say whether it is valid or not, one needs to focus more on the meaning and quality of data than on the quantity. In some domains, such as biomedical and translational sciences, data privacy still holds a higher importance than data sharing. This by default limits access to valuable research data. Intensive discussion, agreements, and conventions among different medical research players, as well as effective techniques and regulations for data anonymization, already made a big step toward simplification of data sharing. However, the situation with the availability of data about rare diseases or outcomes of novel treatments still requires costly and risky clinical trials and, thus, would greatly benefit from smart data generation. Clinical trials and tests on animals initiate a cyclic procedure that may involve multiple redesigns and retesting, which typically takes two or three years for medical devices and up to eight years for novel medicines, and costs between 10 and 20 million euros. The US Food and Drug Administration (FDA) acknowledges that for many novel devices, practical limitations require alternative approaches, such as computer modeling and engineering tests, to conduct large, randomized studies. In this article, we give an overview of global initiatives advocating for computer simulations in support of the 3R principles (Replacement, Reduction, and Refinement) in humane experimentation. We also present several research works that have developed methodologies of smart and comprehensive generation of synthetic biomedical data, such as virtual cohorts of patients, in support of In Silico Clinical Trials (ISCT) and discuss their common ground.

A systematic review of cardiac in-silico clinical trials

Computational models of the heart are now being used to assess the effectiveness and feasibility of interventions through in-silico clinical trials (ISCTs). As the adoption and acceptance of ISCTs increases, best practices for reporting the methodology and analysing the results will emerge. Focusing in the area of cardiology, we aim to evaluate the types of ISCTs, their analysis methods and their reporting standards. To this end, we conducted a systematic review of cardiac ISCTs over the period of 1 January 2012-1 January 2022, following the preferred reporting items for systematic reviews and meta-analysis (PRISMA). We considered cardiac ISCTs of human patient cohorts, and excluded studies of single individuals and those in which models were used to guide a procedure without comparing against a control group. We identified 36 publications that described cardiac ISCTs, with most of the studies coming from the US and the UK. In 75% of the studies, a validation step was performed, although the specific type of validation varied between the studies. ANSYS FLUENT was the most commonly used software in 19% of ISCTs. The specific software used was not reported in 14% of the studies. Unlike clinical trials, we found a lack of consistent reporting of patient demographics, with 28% of the studies not reporting them. Uncertainty quantification was limited, with sensitivity analysis performed in only 19% of the studies. In 97% of the ISCTs, no link was provided to provide easy access to the data or models used in the study. There was no consistent naming of study types with a wide range of studies that could potentially be considered ISCTs. There is a clear need for community agreement on minimal reporting standards on patient demographics, accepted standards for ISCT cohort quality control, uncertainty quantification, and increased model and data sharing.

Novel Baseline Facial Muscle Database Using Statistical Shape Modeling and In Silico Trials toward Decision Support for Facial Rehabilitation

Backgrounds and Objective: Facial palsy is a complex pathophysiological condition affecting the personal and professional lives of the involved patients. Sudden muscle weakness or paralysis needs to be rehabilitated to recover a symmetric and expressive face. Computer-aided decision support systems for facial rehabilitation have been developed. However, there is a lack of facial muscle baseline data to evaluate the patient states and guide as well as optimize the rehabilitation strategy. In this present study, we aimed to develop a novel baseline facial muscle database (static and dynamic behaviors) using the coupling between statistical shape modeling and in-silico trial approaches. Methods: 10,000 virtual subjects (5000 males and 5000 females) were generated from a statistical shape modeling (SSM) head model. Skull and muscle networks were defined so that they statistically fit with the head shapes. Two standard mimics: smiling and kissing were generated. The muscle strains of the lengths in neutral and mimic positions were computed and recorded thanks to the muscle insertion and attachment points on the animated head and skull meshes. For validation, five head and skull meshes were reconstructed from the five computed tomography (CT) image sets. Skull and muscle networks were then predicted from the reconstructed head meshes. The predicted skull meshes were compared with the reconstructed skull meshes based on the mesh-to-mesh distance metrics. The predicted muscle lengths were also compared with those manually defined on the reconstructed head and skull meshes. Moreover, the computed muscle lengths and strains were compared with those in our previous studies and the literature. Results: The skull prediction's median deviations from the CT-based models were 2.2236 mm, 2.1371 mm, and 2.1277 mm for the skull shape, skull mesh, and muscle attachment point regions, respectively. The median deviation of the muscle lengths was 4.8940 mm. The computed muscle strains were compatible with the reported values in our previous Kinect-based method and the literature. Conclusions: The development of our novel facial muscle database opens new avenues to accurately evaluate the facial muscle states of facial palsy patients. Based on the evaluated results, specific types of facial mimic rehabilitation exercises can also be selected optimally to train the target muscles. In perspective, the database of the computed muscle lengths and strains will be integrated into our available clinical decision support system for automatically detecting malfunctioning muscles and proposing patient-specific rehabilitation serious games.

Virtual patients, digital twins and causal disease models: paving the ground for in silico clinical trials

Computational models are being explored to simulate in silico the efficacy and safety of drug candidates and medical devices. Disease models that are based on patients' profiling data are being produced to represent interactomes of genes or proteins and to infer causality in the pathophysiology {AuQ: Edit OK?}, which makes it possible to mimic the impact of drugs on relevant targets. Virtual patients designed from medical records as well as digital twins were generated to simulate specific organs and to predict treatment efficacy at the individual patient level {AuQ: Edit OK?}. As the acceptance of digital evidence by regulators grows, predictive artificial intelligence (AI)-based models will support the design of confirmatory trials in humans and will accelerate the development of efficient drugs and medical devices.

Mapping the use of computational modelling and simulation in clinics: A survey

In silico medicine describes the application of computational modelling and simulation (CM&S) to the study, diagnosis, treatment or prevention of a disease. Tremendous research advances have been achieved to facilitate the use of CM&S in clinical applications. Nevertheless, the uptake of CM&S in clinical practice is not always timely and accurately reflected in the literature. A clear view on the current awareness, actual usage and opinions from the clinicians is needed to identify barriers and opportunities for the future of in silico medicine. The aim of this study was capturing the state of CM&S in clinics by means of a survey toward the clinical community. Responses were collected online using the Virtual Physiological Human institute communication channels, engagement with clinical societies, hospitals and individual contacts, between 2020 and 2021. Statistical analyses were done with R. Participants (n = 163) responded from all over the world. Clinicians were mostly aged between 35 and 64 years-old, with heterogeneous levels of experience and areas of expertise (i.e., 48% cardiology, 13% musculoskeletal, 8% general surgery, 5% paediatrics). The CM&S terms "Personalised medicine" and "Patient-specific modelling" were the most well-known within the respondents. "In silico clinical trials" and "Digital Twin" were the least known. The familiarity with different methods depended on the medical specialty. CM&S was used in clinics mostly to plan interventions. To date, the usage frequency is still scarce. A well-recognized benefit associated to CM&S is the increased trust in planning procedures. Overall, the recorded level of trust for CM&S is high and not proportional to awareness level. The main barriers appear to be access to computing resources, perception that CM&S is slow. Importantly, clinicians see a role for CM&S expertise in their team in the future. This survey offers a snapshot of the current situation of CM&S in clinics. Although the sample size and representativity could be increased, the results provide the community with actionable data to build a responsible strategy for accelerating a positive uptake of in silico medicine. New iterations and follow-up activities will track the evolution of responses over time and contribute to strengthen the engagement with the medical community.

Artificial intelligence and real-world data for drug and food safety - A regulatory science perspective

In 2013, the Global Coalition for Regulatory Science Research (GCRSR) was established with members from over ten countries (www.gcrsr.net). One of the main objectives of GCRSR is to facilitate communication among global regulators on the rise of new technologies with regulatory applications through the annual conference Global Summit on Regulatory Science (GSRS). The 11th annual GSRS conference (GSRS21) focused on "Regulatory Sciences for Food/Drug Safety with Real-World Data (RWD) and Artificial Intelligence (AI)." The conference discussed current advancements in both AI and RWD approaches with a specific emphasis on how they impact regulatory sciences and how regulatory agencies across the globe are pursuing the adaptation and oversight of these technologies. There were presentations from Brazil, Canada, India, Italy, Japan, Germany, Switzerland, Singapore, the United Kingdom, and the United States. These presentations highlighted how various agencies are moving forward with these technologies by either improving the agencies' operation and/or preparing regulatory mechanisms to approve the products containing these innovations. To increase the content and discussion, the GSRS21 hosted two debate sessions on the question of "Is Regulatory Science Ready for AI?" and a workshop to showcase the analytical data tools that global regulatory agencies have been using and/or plan to apply to regulatory science. Several key topics were highlighted and discussed during the conference, such as the capabilities of AI and RWD to assist regulatory science policies for drug and food safety, the readiness of AI and data science to provide solutions for regulatory science. Discussions highlighted the need for a constant effort to evaluate emerging technologies for fit-for-purpose regulatory applications. The annual GSRS conferences offer a unique platform to facilitate discussion and collaboration across regulatory agencies, modernizing regulatory approaches, and harmonizing efforts.

Mechano-biological and bio-mechanical pathways in cutaneous wound healing

Injuries to the skin heal through coordinated action of fibroblast-mediated extracellular matrix (ECM) deposition, ECM remodeling, and wound contraction. Defects involving the dermis result in fibrotic scars featuring increased stiffness and altered collagen content and organization. Although computational models are crucial to unravel the underlying biochemical and biophysical mechanisms, simulations of the evolving wound biomechanics are seldom benchmarked against measurements. Here, we leverage recent quantifications of local tissue stiffness in murine wounds to refine a previously-proposed systems-mechanobiological finite-element model. Fibroblasts are considered as the main cell type involved in ECM remodeling and wound contraction. Tissue rebuilding is coordinated by the release and diffusion of a cytokine wave, e.g. TGF-β, itself developed in response to an earlier inflammatory signal triggered by platelet aggregation. We calibrate a model of the evolving wound biomechanics through a custom-developed hierarchical Bayesian inverse analysis procedure. Further calibration is based on published biochemical and morphological murine wound healing data over a 21-day healing period. The calibrated model recapitulates the temporal evolution of: inflammatory signal, fibroblast infiltration, collagen buildup, and wound contraction. Moreover, it enables in silico hypothesis testing, which we explore by: (i) quantifying the alteration of wound contraction profiles corresponding to the measured variability in local wound stiffness; (ii) proposing alternative constitutive links connecting the dynamics of the biochemical fields to the evolving mechanical properties; (iii) discussing the plausibility of a stretch- vs. stiffness-mediated mechanobiological coupling. Ultimately, our model challenges the current understanding of wound biomechanics and mechanobiology, beside offering a versatile tool to explore and eventually control scar fibrosis after injury.

In Silico Studies to Support Vaccine Development

The progress that has been made in computer science positioned in silico studies as an important and well-recognized methodology in the drug discovery and development process. It has numerous advantages in terms of costs and also plays a huge impact on the way the research is conducted since it can limit the use of animal models leading to more sustainable research. Currently, human trials are already being partly replaced by in silico trials. EMA and FDA are both endorsing these studies and have been providing webinars and guidance to support them. For instance, PBPK modeling studies are being used to gather data on drug interactions with other drugs and are also being used to support clinical and regulatory requirements for the pediatric population, pregnant women, and personalized medicine. This trend evokes the need to understand the role of in silico studies in vaccines, considering the importance that these products achieved during the pandemic and their promising hope in oncology. Vaccines are safer than other current oncology treatments. There is a huge variety of strategies for developing a cancer vaccine, and some of the points that should be considered when designing the vaccine technology are the following: delivery platforms (peptides, lipid-based carriers, polymers, dendritic cells, viral vectors, etc.), adjuvants (to boost and promote inflammation at the delivery site, facilitating immune cell recruitment and activation), choice of the targeted antigen, the timing of vaccination, the manipulation of the tumor environment, and the combination with other treatments that might cause additive or even synergistic anti-tumor effects. These and many other points should be put together to outline the best vaccine design. The aim of this article is to perform a review and comprehensive analysis of the role of in silico studies to support the development of and design of vaccines in the field of oncology and infectious diseases. The authors intend to perform a literature review of all the studies that have been conducted so far in preparing in silico models and methods to support the development of vaccines. From this point, it was possible to conclude that there are few in silico studies on vaccines. Despite this, an overview of how the existing work could support the design of vaccines is described.

Decentralised, patient-centric, site-less, virtual, and digital clinical trials? From confusion to consensus

There is increasing interest in clinical trials that use technologies and other innovative operational approaches to organise trial activities around trial participants instead of investigator sites. A range of terms has been introduced to refer to this operational clinical trial model, including virtual, digital, remote, and decentralised clinical trials (DCTs). However, this lack of standardised terminology can cause confusion over what a particular trial model entails and for what purposes it can be used, hampering discussions by stakeholders on its acceptability and suitability. Here, we review the different terms described in the scientific literature, advocate the consistent use of a unified term, 'decentralised clinical trial,' and provide a detailed definition of this term.

Quantum computing led innovation for achieving a more sustainable Covid-19 healthcare industry

Involvement of multiple stakeholders in healthcare industry, even the simple healthcare problems become complex due to classical approach to treatment. In the Covid-19 era where quick and accurate solutions in healthcare are needed along with quick collaboration of stakeholders such as patients, insurance agents, healthcare providers and medicine supplier etc., a classical computing approach is not enough. Therefore, this study aims to identify the role of quantum computing in disrupting the healthcare sector with the lens of organizational information processing theory (OIPT), creating a more sustainable (less strained) healthcare system. A semi-structured interview approach is adopted to gauge the expectations of professionals from healthcare industry regarding quantum computing. A structured approach of coding, using open, axial and selective approach is adopted to map the themes under quantum computing for healthcare industry. The findings indicate the potential applications of quantum computing for pharmaceutical, hospital, health insurance organizations along with patients to have precise and quick solutions to the problems, where greater accuracy and speed can be achieved. Existing research focuses on the technological background of quantum computing, whereas this study makes an effort to mark the beginning of quantum computing research with respect to organizational management theory.

Synthetic data in health care: A narrative review

Data are central to research, public health, and in developing health information technology (IT) systems. Nevertheless, access to most data in health care is tightly controlled, which may limit innovation, development, and efficient implementation of new research, products, services, or systems. Using synthetic data is one of the many innovative ways that can allow organizations to share datasets with broader users. However, only a limited set of literature is available that explores its potentials and applications in health care. In this review paper, we examined existing literature to bridge the gap and highlight the utility of synthetic data in health care. We searched PubMed, Scopus, and Google Scholar to identify peer-reviewed articles, conference papers, reports, and thesis/dissertations articles related to the generation and use of synthetic datasets in health care. The review identified seven use cases of synthetic data in health care: a) simulation and prediction research, b) hypothesis, methods, and algorithm testing, c) epidemiology/public health research, d) health IT development, e) education and training, f) public release of datasets, and g) linking data. The review also identified readily and publicly accessible health care datasets, databases, and sandboxes containing synthetic data with varying degrees of utility for research, education, and software development. The review provided evidence that synthetic data are helpful in different aspects of health care and research. While the original real data remains the preferred choice, synthetic data hold possibilities in bridging data access gaps in research and evidence-based policymaking.

Methods for Insulin Bolus Adjustment Based on the Continuous Glucose Monitoring Trend Arrows in Type 1 Diabetes: Performance and Safety Assessment in an In Silico Clinical Trial

BACKGROUND

Providing real-time magnitude and direction of glucose rate-of-change (ROC) via trend arrows represents one of the major strengths of continuous glucose monitoring (CGM) sensors in managing type 1 diabetes (T1D). Several literature methods were proposed to adjust the standard formula (SF) used for insulin bolus calculation by accounting for glucose ROC, but each of them provides different suggestions, making it difficult to understand which should be applied in practice. This work aims at performing an extensive in-silico assessment of their performance and safety.

METHODS

The methods of Buckingham (BU), Scheiner (SC), Pettus/Edelman (PE), Klonoff/Kerr (KL), Aleppo/Laffel (AL), Ziegler (ZI), and Bruttomesso (BR) were evaluated using the UVa/Padova T1D simulator, in single-meal scenarios, where ROC and glucose at mealtime varied between [-2,+2] mg/dL/min and [80,200] mg/dL, respectively. Efficacy of postprandial glucose control was quantitatively assessed by time in, above and below range (TIR, TAR, and TBR, respectively).

RESULTS

For negative ROCs, all methods proved to increase TIR and decrease TAR and TBR vs SF, with KL, PE, and BR being the most effective. For positive ROCs, a general worsening of the performances is present, only BR improved the glycemic control when mealtime glucose was close to hypoglycemia, while SC resulted the safest in the other conditions.

CONCLUSIONS

Insulin bolus adjustment methods are effective for negative ROCs, but they generally appear to overdose for positive ROCs, calling for safer strategies in such a scenario. These results can be useful in outlining guidelines to identify which adjustment to apply based on the mealtime condition.