Emerging technologies and their impact on regulatory science

Incorporating new approach methods (NAMs) data in dose-response assessments: The future is now!

Regulatory dose-response assessments traditionally rely on in vivo data and default assumptions. New Approach Methods (NAMs) present considerable opportunities to both augment traditional dose-response assessments and accelerate the evaluation of new/data-poor chemicals. This review aimed to determine the potential utilization of NAMs through a unified conceptual framework that compartmentalizes derivation of toxicity values into five sequential Key Dose-response Modules (KDMs): (1) point-of-departure (POD) determination, (2) test system-to-human (e.g. inter-species) toxicokinetics and (3) toxicodynamics, (4) human population (intra-species) variability in toxicodynamics, and (5) toxicokinetics. After using several "traditional" dose-response assessments to illustrate this framework, a review is presented where existing NAMs, including in silico, in vitro, and in vivo approaches, might be applied across KDMs. Further, the false dichotomy between "traditional" and NAMs-derived data sources is broken down by organizing dose-response assessments into a matrix where each KDM has Tiers of increasing precision and confidence: Tier 0: Default/generic values, Tier 1: Computational predictions, Tier 2: Surrogate measurements, and Tier 3: Direct measurements. These findings demonstrated that although many publications promote the use of NAMs in KDMs (1) for POD determination and (5) for human population toxicokinetics, the proposed matrix of KDMs and Tiers reveals additional immediate opportunities for NAMs to be integrated across other KDMs. Further, critical needs were identified for developing NAMs to improve in vitro dosimetry and quantify test system and human population toxicodynamics. Overall, broadening the integration of NAMs across the steps of dose-response assessment promises to yield higher throughput, less animal-dependent, and more science-based toxicity values for protecting human health.

AI and ML-based risk assessment of chemicals: predicting carcinogenic risk from chemical-induced genomic instability

Chemical risk assessment plays a pivotal role in safeguarding public health and environmental safety by evaluating the potential hazards and risks associated with chemical exposures. In recent years, the convergence of artificial intelligence (AI), machine learning (ML), and omics technologies has revolutionized the field of chemical risk assessment, offering new insights into toxicity mechanisms, predictive modeling, and risk management strategies. This perspective review explores the synergistic potential of AI/ML and omics in deciphering clastogen-induced genomic instability for carcinogenic risk prediction. We provide an overview of key findings, challenges, and opportunities in integrating AI/ML and omics technologies for chemical risk assessment, highlighting successful applications and case studies across diverse sectors. From predicting genotoxicity and mutagenicity to elucidating molecular pathways underlying carcinogenesis, integrative approaches offer a comprehensive framework for understanding chemical exposures and mitigating associated health risks. Future perspectives for advancing chemical risk assessment and cancer prevention through data integration, advanced machine learning techniques, translational research, and policy implementation are discussed. By implementing the predictive capabilities of AI/ML and omics technologies, researchers and policymakers can enhance public health protection, inform regulatory decisions, and promote sustainable development for a healthier future.

Establishing a national biosafety and biosecurity agency for the United States

The rapid advancement of biological research and biotechnology requires a novel and robust regulatory agency to ensure uniform biosafety and biosecurity governance in the United States. The current fragmented regulatory landscape needs to be refocused to address the complexities of modern biological research, including risks associated with accidental, inadvertent, and deliberate biological incidents. An independent government agency, which we call the National Biosafety and Biosecurity Agency (NBBA), that is devoted to biosafety and biosecurity could effectively address these challenges. The NBBA would consolidate various regulatory functions, streamline processes, and enhance oversight. This oversight would encompass life sciences research in the United States, regardless of the source of funding or level of classification. The agency could also contribute to the bioeconomy by streamlining requirements to safeguard public health and the environment while fostering scientific and commercial progress. The proposed agency would govern high-risk biological pathogens, manage the Federal Select Agent Program, enforce policies related to dual use research of concern, pathogens with enhanced pandemic potential, and nucleic acid synthesis screening, administer regulations on the use and care of laboratory animals, as well as regulate other relevant biosafety and biosecurity activities. The goal would be to provide one-stop shopping for the biomedical research and biotechnology sectors subject to oversight by the Federal government. To ensure leadership in global biosafety and biosecurity, the agency's mission would include international collaboration, applied research, education, workforce development, and coordination with national security initiatives. Creating an agency like the NBBA will be politically challenging but presenting a comprehensive vision and engaging stakeholders early and frequently, and being transparent in the process, will be essential for garnering support. Creating a unified biosafety and biosecurity governance system in the United States will ensure the safe and secure advancement of biological research while sustaining innovation and maintaining international competitiveness.

Bridging the gap: Innovative human-based in vitro approaches for nanomaterials hazard assessment and their role in safe and sustainable by design, risk assessment, and life cycle assessment

The application of nanomaterials in industry and consumer products is growing exponentially, which has pressed the development and use of predictive human in vitro models in pre-clinical analysis to closely extrapolate potential toxic effects in vivo. The conventional cytotoxicity investigation of nanomaterials using cell lines from cancer origin and culturing them two-dimensionally in a monolayer without mimicking the proper pathophysiological microenvironment may affect a precise prediction of in vitro effects at in vivo level. In recent years, complex in vitro models (also belonging to the new approach methodologies, NAMs) have been established in unicellular to multicellular cultures either by using cell lines, primary cells or induced pluripotent stem cells (iPSCs), and reconstituted into relevant biological dimensions mimicking in vivo conditions. These advanced in vitro models retain physiologically reliant exposure scenarios particularly appropriate for oral, dermal, respiratory, and intravenous administration of nanomaterials, which have the potential to improve the in vivo predictability and lead to reliable outcomes. In this perspective, we discuss recent developments and breakthroughs in using advanced human in vitro models for hazard assessment of nanomaterials. We identified fit-for-purpose requirements and remaining challenges for the successful implementation of in vitro data into nanomaterials Safe and Sustainable by Design (SSbD), Risk Assessment (RA), and Life Cycle Assessment (LCA). By addressing the gap between in vitro data generation and the utility of in vitro data for nanomaterial safety assessments, a prerequisite for SSbD approaches, we outlined potential key areas for future development.

WHO-listed authorities (WLA) framework: transparent evidence-based approach for promoting regulatory reliance towards increased access to quality-assured medical products

Background

Increased global access to safe, effective and quality-assured medical products remains a primary goal for the full realization of the World Health Assembly Resolution WHA 67.20 on regulatory systems strengthening for medical products as well as target 3.8 of the Sustainable Development Goals (SDG). To promote the development of efficient regulatory systems, the WHO introduced the Global Benchmarking Tool (GBT) in 2016, upon which the WHO-Listed Authority (WLA) framework was later established. This study aimed to appraise the development of the WLA framework across various phases while highlighting its achievements, challenges, and areas for improvement.

Methods

An exploratory study design using a qualitative approach was used to gather information from relevant documents as well as views and experiences from purposefully selected participants from diverse backgrounds. Data was collected using a combination of desk reviews and In-depth one-to-one or small group interviews employing semi-structured interview guides with open-ended questions. Data was analysed using an inductive thematic analysis approach.

Results

The leading role of the WHO was noted in developing and implementing essential documents and mediating consultative processes among stakeholders. The framework was revealed to bring an evidence-based, inclusive, and transparent approach to recognizing regulatory authorities (RAs) operating at the highest standards of performance. The framework was anticipated to promote regulatory reliance among all RAs, the WHO's prequalification programme, and procurement agencies. Furthermore, remarkable progress towards WLA listing was noted among transitional WLAs including the Stringent Regulatory Authorities (SRAs). Challenges related to the availability of resources, resistance to change, and complexity were associated with the framework.

Conclusion

The study provides a well-rounded view with regard to the roles of the WHO, Member States and other stakeholders in establishing and operationalizing the WLA framework. Furthermore, evaluating the performance and possible WLA designation of RAs operating at international regulatory standards underscores its high relevance in contributing to public health globally. Maintenance along with timely addressing of highlighted next steps to improve the framework particularly in creating better understanding, more communication, and coordination are highly encouraged.

Recent progress in artificial intelligence and machine learning for novel diabetes mellitus medications development

Diabetes mellitus, stemming from either insulin resistance or inadequate insulin secretion, represents a complex ailment that results in prolonged hyperglycemia and severe complications. Patients endure severe ramifications such as kidney disease, vision impairment, cardiovascular disorders, and susceptibility to infections, leading to significant physical suffering and imposing substantial socio-economic burdens. This condition has evolved into an increasingly severe health crisis. There is an urgent need to develop new treatments with improved efficacy and fewer adverse effects to meet clinical demands. However, novel drug development is costly, time-consuming, and often associated with side effects and suboptimal efficacy, making it a major challenge. Artificial Intelligence (AI) and Machine Learning (ML) have revolutionized drug development across its comprehensive lifecycle, spanning drug discovery, preclinical studies, clinical trials, and post-market surveillance. These technologies have significantly accelerated the identification of promising therapeutic candidates, optimized trial designs, and enhanced post-approval safety monitoring. Recent advances in AI, including data augmentation, interpretable AI, and integration of AI with traditional experimental methods, offer promising strategies for overcoming the challenges inherent in AI-based drug discovery. Despite these advancements, there exists a notable gap in comprehensive reviews detailing AI and ML applications throughout the entirety of developing medications for diabetes mellitus. This review aims to fill this gap by evaluating the impact and potential of AI and ML technologies at various stages of diabetes mellitus drug development. It does that by synthesizing current research findings and technological advances so as to effectively control diabetes mellitus and mitigate its far-reaching social and economic impacts. The integration of AI and ML promises to revolutionize diabetes mellitus treatment strategies, offering hope for improved patient outcomes and reduced healthcare burdens worldwide.

Healthcare leaders navigating complexity: a scoping review of key trends in future roles and competencies

BACKGROUND

As healthcare systems rapidly become more complex, healthcare leaders are navigating expanding role scopes and increasingly varied tasks to ensure the provision of high-quality patient care. Despite a range of leadership theories, models, and training curricula to guide leadership development, the roles and competencies required by leaders in the context of emerging healthcare challenges (e.g., disruptive technologies, ageing populations, and burnt-out workforces) have not been sufficiently well conceptualized. This scoping review aimed to examine these roles and competencies through a deep dive into the contemporary academic and targeted gray literature on future trends in healthcare leadership roles and competencies.

METHODS

Three electronic databases (Business Source Premier, Medline, and Embase) were searched from January 2018 to February 2023 for peer-reviewed literature on key future trends in leadership roles and competencies. Websites of reputable healthcare- and leadership-focused organizations were also searched. Data were analyzed using descriptive statistics and thematic analysis to explore both the range and depth of literature and the key concepts underlying leadership roles and competencies.

RESULTS

From an initial 348 articles identified in the literature and screened for relevance, 39 articles were included in data synthesis. Future leadership roles and competencies were related to four key themes: innovation and adaptation (e.g., flexibility and vision setting), collaboration and communication (e.g., relationship and trust building), self-development and self-awareness (e.g., experiential learning and self-examination), and consumer and community focus (e.g., public health messaging). In each of these areas, a broad range of strategies and approaches contributed to effective leadership under conditions of growing complexity, and a diverse array of contexts and situations for which these roles and competencies are applicable.

CONCLUSIONS

This research highlights the inherent interdependence of leadership requirements and health system complexity. Rather than as sets of roles and competencies, effective healthcare leadership might be better conceptualized as a set of broad goals to pursue that include fostering collaboration amongst stakeholders, building cultures of capacity, and continuously innovating for improved quality of care.

Complex or not too complex? One size does not fit all in next generation microphysiological systems

In the attempt to overcome the increasingly recognized shortcomings of existing in vitro and in vivo models, researchers have started to implement alternative models, including microphysiological systems. First examples were represented by 2.5D systems, such as microfluidic channels covered by cell monolayers as blood vessel replicates. In recent years, increasingly complex microphysiological systems have been developed, up to multi-organ on chip systems, connecting different 3D tissues in the same device. However, such an increase in model complexity raises several questions about their exploitation and implementation into industrial and clinical applications, ranging from how to improve their reproducibility, robustness, and reliability to how to meaningfully and efficiently analyze the huge amount of heterogeneous datasets emerging from these devices. Considering the multitude of envisaged applications for microphysiological systems, it appears now necessary to tailor their complexity on the intended purpose, being academic or industrial, and possibly combine results deriving from differently complex stages to increase their predictive power.

Big Question to Developing Solutions: A Decade of Progress in the Development of Aquatic New Approach Methodologies from 2012 to 2022

In 2012, 20 key questions related to hazard and exposure assessment and environmental and health risks of pharmaceuticals and personal care products in the natural environment were identified. A decade later, this article examines the current level of knowledge around one of the lowest-ranking questions at that time, number 19: "Can nonanimal testing methods be developed that will provide equivalent or better hazard data compared with current in vivo methods?" The inclusion of alternative methods that replace, reduce, or refine animal testing within the regulatory context of risk and hazard assessment of chemicals generally faces many hurdles, although this varies both by organism (human-centric vs. other), sector, and geographical region or country. Focusing on the past 10 years, only works that might reasonably be considered to contribute to advancements in the field of aquatic environmental risk assessment are highlighted. Particular attention is paid to methods of contemporary interest and importance, representing progress in (1) the development of methods which provide equivalent or better data compared with current in vivo methods such as bioaccumulation, (2) weight of evidence, or (3) -omic-based applications. Evolution and convergence of these risk assessment areas offer the basis for fundamental frameshifts in how data are collated and used for the protection of taxa across the breadth of the aquatic environment. Looking to the future, we are at a tipping point, with a need for a global and inclusive approach to establish consensus. Bringing together these methods (both new and old) for regulatory assessment and decision-making will require a concerted effort and orchestration. Environ Toxicol Chem 2024;43:559-574. © 2023 The Authors. Environmental Toxicology and Chemistry published by Wiley Periodicals LLC on behalf of SETAC.

Ten years of using key characteristics of human carcinogens to organize and evaluate mechanistic evidence in IARC Monographs on the identification of carcinogenic hazards to humans: Patterns and associations

Systematic review and evaluation of mechanistic evidence using the Key Characteristics approach was proposed by the International Agency for Research on Cancer (IARC) in 2012 and used by the IARC Monographs Working Groups since 2015. Key Characteristics are 10 features of agents known to cause cancer in humans. From 2015 to 2022, a total of 19 Monographs (73 agents combined) used Key Characteristics for cancer hazard classification. We hypothesized that a retrospective analysis of applications of the Key Characteristics approach to cancer hazard classification using heterogenous mechanistic data on diverse agents would be informative for systematic reviews in decision-making. We extracted information on the conclusions, data types, and the role mechanistic data played in the cancer hazard classification from each Monograph. Statistical analyses identified patterns in the use of Key Characteristics, as well as trends and correlations among Key Characteristics, data types, and ultimate decisions. Despite gaps in data for many agents and Key Characteristics, several significant results emerged. Mechanistic data from in vivo animal, in vitro animal, and in vitro human studies were most impactful in concluding that an agent could cause cancer via a Key Characteristic. To exclude the involvement of a Key Characteristic, data from large-scale systematic in vitro testing programs such as ToxCast, were most informative. Overall, increased availability of systemized data streams, such as human in vitro data, would provide the basis for more confident and informed conclusions about both positive and negative associations and inform expert judgments on cancer hazard.

Protecting Human and Animal Health: The Road from Animal Models to New Approach Methods

Animals and animal models have been invaluable for our current understanding of human and animal biology, including physiology, pharmacology, biochemistry, and disease pathology. However, there are increasing concerns with continued use of animals in basic biomedical, pharmacological, and regulatory research to provide safety assessments for drugs and chemicals. There are concerns that animals do not provide sufficient information on toxicity and/or efficacy to protect the target population, so scientists are utilizing the principles of replacement, reduction, and refinement (the 3Rs) and increasing the development and application of new approach methods (NAMs). NAMs are any technology, methodology, approach, or assay used to understand the effects and mechanisms of drugs or chemicals, with specific focus on applying the 3Rs. Although progress has been made in several areas with NAMs, complete replacement of animal models with NAMs is not yet attainable. The road to NAMs requires additional development, increased use, and, for regulatory decision making, usually formal validation. Moreover, it is likely that replacement of animal models with NAMs will require multiple assays to ensure sufficient biologic coverage. The purpose of this manuscript is to provide a balanced view of the current state of the use of animal models and NAMs as approaches to development, safety, efficacy, and toxicity testing of drugs and chemicals. Animals do not provide all needed information nor do NAMs, but each can elucidate key pieces of the puzzle of human and animal biology and contribute to the goal of protecting human and animal health. SIGNIFICANCE STATEMENT: Data from traditional animal studies have predominantly been used to inform human health safety and efficacy. Although it is unlikely that all animal studies will be able to be replaced, with the continued advancement in new approach methods (NAMs), it is possible that sometime in the future, NAMs will likely be an important component by which the discovery, efficacy, and toxicity testing of drugs and chemicals is conducted and regulatory decisions are made.

Algae-Derived Natural Products in Diabetes and Its Complications-Current Advances and Future Prospects

Diabetes poses a significant global health challenge, necessitating innovative therapeutic strategies. Natural products and their derivatives have emerged as promising candidates for diabetes management due to their diverse compositions and pharmacological effects. Algae, in particular, have garnered attention for their potential as a source of bioactive compounds with anti-diabetic properties. This review offers a comprehensive overview of algae-derived natural products for diabetes management, highlighting recent developments and future prospects. It underscores the pivotal role of natural products in diabetes care and delves into the diversity of algae, their bioactive constituents, and underlying mechanisms of efficacy. Noteworthy algal derivatives with substantial potential are briefly elucidated, along with their specific contributions to addressing distinct aspects of diabetes. The challenges and limitations inherent in utilizing algae for therapeutic interventions are examined, accompanied by strategic recommendations for optimizing their effectiveness. By addressing these considerations, this review aims to chart a course for future research in refining algae-based approaches. Leveraging the multifaceted pharmacological activities and chemical components of algae holds significant promise in the pursuit of novel antidiabetic treatments. Through continued research and the fine-tuning of algae-based interventions, the global diabetes burden could be mitigated, ultimately leading to enhanced patient outcomes.

Ten Years of Using Key Characteristics of Human Carcinogens to Organize and Evaluate Mechanistic Evidence in IARC Monographs on the Identification of Carcinogenic Hazards to Humans: Patterns and Associations

Systematic review and evaluation of the mechanistic evidence only recently been instituted in cancer hazard identification step of decision-making. One example of organizing and evaluating mechanistic evidence is the Key Characteristics approach of the International Agency for Research on Cancer (IARC) Monographs on the Identification of Carcinogenic Hazards to Humans. The Key Characteristics of Human Carcinogens were proposed almost 10 years ago and have been used in every IARC Monograph since 2015. We investigated the patterns and associations in the use of Key Characteristics by the independent expert Working Groups. We examined 19 Monographs (2015-2022) that evaluated 73 agents. We extracted information on the conclusions by each Working Group on the strength of evidence for agent-Key Characteristic combinations, data types that were available for decisions, and the role mechanistic data played in the final cancer hazard classification. We conducted both descriptive and association analyses within and across data types. We found that IARC Working Groups were cautious when evaluating mechanistic evidence: for only ∼13% of the agents was strong evidence assigned for any Key Characteristic. Genotoxicity and cell proliferation were most data-rich, while little evidence was available for DNA repair and immortalization Key Characteristics. Analysis of the associations among Key Characteristics revealed that only chemical's metabolic activation was significantly co-occurring with genotoxicity and cell proliferation/death. Evidence from exposed humans was limited, while mechanistic evidence from rodent studies in vivo was often available. Only genotoxicity and cell proliferation/death were strongly associated with decisions on whether mechanistic data was impactful on the final cancer hazard classification. The practice of using the Key Characteristics approach is now well-established at IARC Monographs and other government agencies and the analyses presented herein will inform the future use of mechanistic evidence in regulatory decision-making.

Integrative Chemical-Biological Grouping of Complex High Production Volume Substances from Lower Olefin Manufacturing Streams

Human cell-based test methods can be used to evaluate potential hazards of mixtures and products of petroleum refining ("unknown or variable composition, complex reaction products, or biological materials" substances, UVCBs). Analyses of bioactivity and detailed chemical characterization of petroleum UVCBs were used separately for grouping these substances; a combination of the approaches has not been undertaken. Therefore, we used a case example of representative high production volume categories of petroleum UVCBs, 25 lower olefin substances from low benzene naphtha and resin oils categories, to determine whether existing manufacturing-based category grouping can be supported. We collected two types of data: nontarget ion mobility spectrometry-mass spectrometry of both neat substances and their organic extracts and in vitro bioactivity of the organic extracts in five human cell types: umbilical vein endothelial cells and induced pluripotent stem cell-derived hepatocytes, endothelial cells, neurons, and cardiomyocytes. We found that while similarity in composition and bioactivity can be observed for some substances, existing categories are largely heterogeneous. Strong relationships between composition and bioactivity were observed, and individual constituents that determine these associations were identified. Overall, this study showed a promising approach that combines chemical composition and bioactivity data to better characterize the variability within manufacturing categories of petroleum UVCBs.

Society for birth defects research and prevention's multidisciplinary research needs workshop 2022: A call to action

The Society for Birth Defects Research and Prevention (BDRP) strives to understand and protect against potential hazards to developing embryos, fetuses, children, and adults by bringing together scientific knowledge from diverse fields. The theme of 62nd Annual Meeting of BDRP, "From Bench to Bedside and Back Again", represented the cutting-edge research areas of high relevance to public health and significance in the fields of birth defects research and surveillance. The multidisciplinary Research Needs Workshop (RNW) convened at the Annual Meeting continues to identify pressing knowledge gaps and encourage interdisciplinary research initiatives. The multidisciplinary RNW was first introduced at the 2018 annual meeting to provide an opportunity for annual meeting attendees to participate in breakout discussions on emerging topics in birth defects research and to foster collaboration between basic researchers, clinicians, epidemiologists, drug developers, industry partners, funding agencies, and regulators to discuss state-of-the-art methods and innovative projects. Initially, a list of workshop topics was compiled by the RNW planning committee and circulated among the members of BDRP to obtain the most popular topics for the Workshop discussions. Based on the pre-meeting survey results, the top three discussion topics selected were, A) Inclusion of pregnant and lactating women in clinical trials. When, why, and how? B) Building multidisciplinary teams across disciplines: What cross-training is needed? And C) Challenges in applications of Artificial Intelligence (AI) and machine learning for risk factor analysis in birth defects research. This report summarizes the key highlights of the RNW workshop and specific topic discussions.

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.

Trends and opportunities in computable clinical phenotyping: A scoping review

Identifying patient cohorts meeting the criteria of specific phenotypes is essential in biomedicine and particularly timely in precision medicine. Many research groups deliver pipelines that automatically retrieve and analyze data elements from one or more sources to automate this task and deliver high-performing computable phenotypes. We applied a systematic approach based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines to conduct a thorough scoping review on computable clinical phenotyping. Five databases were searched using a query that combined the concepts of automation, clinical context, and phenotyping. Subsequently, four reviewers screened 7960 records (after removing over 4000 duplicates) and selected 139 that satisfied the inclusion criteria. This dataset was analyzed to extract information on target use cases, data-related topics, phenotyping methodologies, evaluation strategies, and portability of developed solutions. Most studies supported patient cohort selection without discussing the application to specific use cases, such as precision medicine. Electronic Health Records were the primary source in 87.1 % (N = 121) of all studies, and International Classification of Diseases codes were heavily used in 55.4 % (N = 77) of all studies, however, only 25.9 % (N = 36) of the records described compliance with a common data model. In terms of the presented methods, traditional Machine Learning (ML) was the dominant method, often combined with natural language processing and other approaches, while external validation and portability of computable phenotypes were pursued in many cases. These findings revealed that defining target use cases precisely, moving away from sole ML strategies, and evaluating the proposed solutions in the real setting are essential opportunities for future work. There is also momentum and an emerging need for computable phenotyping to support clinical and epidemiological research and precision medicine.

Adaptability of AI for safety evaluation in regulatory science: A case study of drug-induced liver injury

Artificial intelligence (AI) has played a crucial role in advancing biomedical sciences but has yet to have the impact it merits in regulatory science. As the field advances, in silico and in vitro approaches have been evaluated as alternatives to animal studies, in a drive to identify and mitigate safety concerns earlier in the drug development process. Although many AI tools are available, their acceptance in regulatory decision-making for drug efficacy and safety evaluation is still a challenge. It is a common perception that an AI model improves with more data, but does reality reflect this perception in drug safety assessments? Importantly, a model aiming at regulatory application needs to take a broad range of model characteristics into consideration. Among them is adaptability, defined as the adaptive behavior of a model as it is retrained on unseen data. This is an important model characteristic which should be considered in regulatory applications. In this study, we set up a comprehensive study to assess adaptability in AI by mimicking the real-world scenario of the annual addition of new drugs to the market, using a model we previously developed known as DeepDILI for predicting drug-induced liver injury (DILI) with a novel Deep Learning method. We found that the target test set plays a major role in assessing the adaptive behavior of our model. Our findings also indicated that adding more drugs to the training set does not significantly affect the predictive performance of our adaptive model. We concluded that the proposed adaptability assessment framework has utility in the evaluation of the performance of a model over time.

Challenges and opportunities for mining adverse drug reactions: perspectives from pharma, regulatory agencies, healthcare providers and consumers

Monitoring drug safety is a central concern throughout the drug life cycle. Information about toxicity and adverse events is generated at every stage of this life cycle, and stakeholders have a strong interest in applying text mining and artificial intelligence (AI) methods to manage the ever-increasing volume of this information. Recognizing the importance of these applications and the role of challenge evaluations to drive progress in text mining, the organizers of BioCreative VII (Critical Assessment of Information Extraction in Biology) convened a panel of experts to explore 'Challenges in Mining Drug Adverse Reactions'. This article is an outgrowth of the panel; each panelist has highlighted specific text mining application(s), based on their research and their experiences in organizing text mining challenge evaluations. While these highlighted applications only sample the complexity of this problem space, they reveal both opportunities and challenges for text mining to aid in the complex process of drug discovery, testing, marketing and post-market surveillance. Stakeholders are eager to embrace natural language processing and AI tools to help in this process, provided that these tools can be demonstrated to add value to stakeholder workflows. This creates an opportunity for the BioCreative community to work in partnership with regulatory agencies, pharma and the text mining community to identify next steps for future challenge evaluations.

Microphysiological Systems Evaluation: Experience of TEX-VAL Tissue Chip Testing Consortium

Much has been written and said about the promise and excitement of microphysiological systems, miniature devices that aim to recreate aspects of human physiology on a chip. The rapid explosion of the offerings and persistent publicity placed high expectations on both product manufacturers and regulatory agencies to adopt the data. Inevitably, discussions of where this technology fits in chemical testing paradigms are ongoing. Some end-users became early adopters, whereas others have taken a more cautious approach because of the high cost and uncertainties of their utility. Here, we detail the experience of a public-private collaboration established for testing of diverse microphysiological systems. Collectively, we present a number of considerations on practical aspects of using microphysiological systems in the context of their applications in decision-making. Specifically, future end-users need to be prepared for extensive on-site optimization and have access to a wide range of imaging and other equipment. We reason that cells, related reagents, and the technical skills of the research staff, not the devices themselves, are the most critical determinants of success. Extrapolation from concentration-response effects in microphysiological systems to human blood or oral exposures, difficulties with replicating the whole organ, and long-term functionality remain as critical challenges. Overall, we conclude that it is unlikely that a rodent- or human-equivalent model is achievable through a finite number of microphysiological systems in the near future; therefore, building consensus and promoting the gradual incorporation of these models into tiered approaches for safety assessment and decision-making is the sensible path to wide adoption.

Artificial Intelligence-Based Pharmacovigilance in the Setting of Limited Resources

With the rapid development of artificial intelligence (AI) technologies, and the large amount of pharmacovigilance-related data stored in an electronic manner, data-driven automatic methods need to be urgently applied to all aspects of pharmacovigilance to assist healthcare professionals. However, the quantity and quality of data directly affect the performance of AI, and there are particular challenges to implementing AI in limited-resource settings. Analyzing challenges and solutions for AI-based pharmacovigilance in resource-limited settings can improve pharmacovigilance frameworks and capabilities in these settings. In this review, we summarize the challenges into four categories: establishing a database for an AI-based pharmacovigilance system, lack of human resources, weak AI technology and insufficient government support. This study also discusses possible solutions and future perspectives on AI-based pharmacovigilance in resource-limited settings.