Category: AI HEOR

  • Ensuring Loon’s Compliance with NICE Guidelines on AI Use in Evidence Synthesis

    Ensuring Loon’s Compliance with NICE Guidelines on AI Use in Evidence Synthesis

    In this article, we navigate NICE’s Position on the Use of AI in Evidence Generation for Health Technology Assessment (HTA) and explain how Loon Hatch™ – our end-to-end, fully automated, and expert-validated evidence synthesis solution – and Loon Lens™ – our scientifically validated, autonomous literature screener – align with the HTA body’s’ guidelines on the use of AI in Health Economics and Outcomes Research (HEOR).

    NICE AI Position

    Revolutionizing Evidence Synthesis with AI: Loon’s Compliance with NICE Guidelines

    The National Institute for Health and Care Excellence (NICE) has recently released guidelines on the responsible use of AI in evidence synthesis for HTA. At Loon, we’re delighted to demonstrate how our AI-powered solutions, such as Loon Hatch™ and Loon Lens ™, align seamlessly with these guidelines. At Loon, we’re not just meeting these guidelines — we’re exceeding them and setting new standards in speed, accuracy, and compliance for Market Access, HTA, and HEOR workflows.

    Loon’s AI Solutions: Exceeding NICE Standards

    Our end-to-end AI-powered solutions for evidence synthesis are designed to redefine evidence synthesis while adhering to NICE’s stringent guidelines:

    NICE GuidelineLoon’s Approach to Compliance
    Human OversightLoon Hatch™ AI outputs are always assessed and validated by human experts, ensuring efficiency and accuracy.
    Validation Audit TraceWe show when and why an expert overrode an AI recommendation, ensuring that all validation decisions are transparent and traceable, enhancing accountability and trust in the AI system.
    Scientific MethodologyLoon offers full disclosure of the scientific methodologies used in our AI systems, including validation data.
    Transparency and JustificationLoon provides clear explanations of AI’s role and outcomes through comprehensive documentation, allowing users to track and verify AI decisions alongside expert assessments.
    Ethical and Legal ComplianceLoon ensures strict adherence to legal frameworks and ethical guidelines, including GDPR, for data protection and fairness.
    Security and Risk MitigationRobust cybersecurity measures and risk management strategies such as air-gapping are in place to protect AI systems and prevent cyber incidents.
    Detailed ReportingLoon maintains thorough documentation of AI operations, ensuring transparency and continuous improvement.
    Early Engagement with NICELoon will initiate proactive dialogue with NICE to align AI methods with their frameworks right from the start.


    Scientific Validation: Loon Lens™ Literature Screener

    Loon Lens™, our fully automated literature screener, has undergone rigorous scientific validation to ensure its accuracy and reliability in identifying relevant studies for systematic reviews. Recently, Loon published a validation paper detailing the performance of Loon Lens™ on medRxiv, which demonstrates an accuracy of 95.5% (95% CI: 94.8–96.1), with sensitivity (recall) at 98.95% (95% CI: 97.57–100%) and specificity at 95.24% (95% CI: 94.54–95.89%). These results set a new standard for AI-assisted literature screening. This paper offers full transparency on the methodologies used, model performance, and validation processes, fostering trust and credibility in AI-driven research.

    For a more detailed view of the paper, please refer to the full text and article metrics on medRxiv.

    Transforming Evidence Synthesis with Loon Hatch™

    Loon Hatch™ leverages our patent-pending Cognitive Ensemble AI Systems™ to revolutionize the evidence synthesis process:

    Aligning with NICE’s Vision for AI in HTA

    NICE emphasizes AI as a tool to enhance, not replace, human involvement in evidence synthesis. This aligns perfectly with Loon’s approach. For instance, Loon Hatch™ rapidly processes vast amounts of literature, but human experts make the final inclusion decisions.

    Our solutions comply with NICE’s recommendations on machine learning (ML) and large language models (LLMs) in evidence synthesis:

    All of these processes are conducted with rigorous expert oversight, ensuring accuracy and reliability.

    Loon’s Commitment to Responsible AI Use

    As we continue to innovate, we remain deeply committed to adhering to industry standards and guidelines, ensuring that our AI solutions automate processes and enhance efficiency while also meeting the highest standards of transparency and ethical use. Our collaboration with regulatory bodies and profound understanding of clinical research challenges position us as leaders in the future of evidence synthesis.

    By choosing Loon Hatch™, you are accelerating your evidence synthesis process and ensuring full compliance with the latest industry guidelines, making your HTA submissions more robust and reliable.

    Ready to Transform Your Evidence Synthesis Process?

    Contact us today for a demo, or visit loonbio.com to learn more about how we’re revolutionizing market access and clinical research with AI-driven solutions that reduce research timelines from years to days.


    About Loon

    Loon Inc. is at the forefront of AI-driven market access and clinical research. We help biopharma companies navigate the complexities of market access with confidence, providing innovative solutions that dramatically reduce research timelines while maintaining the highest standards of quality and compliance.

  • Making Systematic Reviews Feasible for Every Clinical Trial with Loon Hatch™ and Revolutionizing Clinical Research

    Making Systematic Reviews Feasible for Every Clinical Trial with Loon Hatch™ and Revolutionizing Clinical Research

    Can starting and ending clinical trials with Systematic Reviews truly be feasible? It hasn’t been—until now!

    In the world of clinical research, systematic reviews are essential for ensuring that trials are well-informed, ethically sound, and impactful. Yet, a recent study by Clarke et al. uncovered a concerning trend: out of 175 randomized controlled trial (RCT) reports published over 25 years in five top-tier medical journals, only 2.9% referenced up-to-date systematic reviews in their Introduction sections. Even more alarming, just 3.4% incorporated their findings into an updated systematic review in the Discussion sections.

    The Problem: Research Gaps That Could Cost Lives

    These numbers are not just disappointing—they’re dangerous. Without systematic reviews, clinical trials risk:

    The Reality: Systematic Reviews Are Time-Consuming and Resource-Intensive

    It’s easy to say that systematic reviews should be integrated into every stage of a clinical trial, but the reality is far from simple. The average systematic review takes 2,500 person-hours and several expert reviewers to complete. Considering that each clinical trial would require at least two systematic reviews, you’re looking at an additional 5,000 person-hours—a significant strain on already limited resources.

    The Solution: Loon Hatch™ – Automating Systematic Reviews for the Future of Clinical Research

    This is where Loon Hatch™ comes in. At Loon, we’ve developed a groundbreaking tool that automates the systematic review process, making it possible to maintain living systematic reviews—rapidly and effortlessly.

    With Loon Hatch™, the once daunting task of integrating systematic reviews into clinical trials becomes a seamless part of the research process. Imagine being able to:

    And when it comes to updating existing systematic reviews with new trial results? With Loon Hatch™, it’s as simple as publishing your findings. Our tool automatically updates your living systematic review, ensuring that your research remains at the cutting edge.

    The Future is Now: Join Us in Advancing Evidence-Informed Research

    AI-enabled technologies like Loon Hatch™ are transforming the future of clinical research, making it possible and practical to integrate systematic reviews at every stage of a clinical trial. This isn’t just a step forward, towards a more ethical, efficient, and impactful research process.

    Let’s connect and explore how we can push the boundaries of evidence-informed research together. The future of clinical research is truly exciting, and with tools like Loon Hatch™, we’re just getting started.

  • AI Literature Screening: Revolutionizing Systematic Reviews with Artificial Intelligence

    AI Literature Screening: Revolutionizing Systematic Reviews with Artificial Intelligence

    Introduction

    In the rapidly evolving landscape of research, AI literature screening stands out as a transformative force. By leveraging artificial intelligence, researchers can sift through vast amounts of literature with unprecedented speed and accuracy. This innovation accelerates the research process to ensure a more comprehensive and thorough review of existing knowledge. In this article, we delve into the intricacies of AI literature screening, exploring its benefits, tools, applications, and future trends.

    Understanding AI Literature Screening

    Definition and Importance
    AI literature screening refers to the use of artificial intelligence technologies to automate the process of reviewing academic and scientific literature. This approach is crucial in managing the overwhelming volume of publications and ensuring that researchers can access relevant and high-quality information efficiently. Historically, literature screening has been a labour-intensive and time-consuming process, often susceptible to human error and bias.

    How AI Literature Screening Works

    Algorithms and Machine Learning
    At the core of AI literature screening are sophisticated algorithms and machine learning models. These technologies analyze text data, identify relevant patterns, and classify information based on predefined criteria. Natural Language Generation (NLG) plays a vital role in understanding and interpreting the nuances of human language, enabling AI to comprehend and process large volumes of literature accurately. One notable example is our Cognitive Ensemble AI System™, which integrates multiple AI agents to enhance speed and accuracy.

    Benefits of AI Literature Screening

    Efficiency and Accuracy
    One of the primary benefits of AI literature screening is its efficiency. AI systems can process thousands of documents in a fraction of the time it would take a human. This rapid processing capability is coupled with high accuracy, reducing the likelihood of missing critical information or including irrelevant data. Moreover, AI systems can continuously learn and improve from new data, enhancing their performance over time.

    Cost-Effectiveness
    Implementing AI literature screening can also be cost-effective. By automating the screening process, organizations can save time and money on repetitive tasks and reallocate resources to other critical areas of research. This economic advantage makes AI an attractive option for institutions operating with limited budgets.

    Comprehensive Analysis
    AI literature screening ensures a more comprehensive analysis by covering a broader range of sources and identifying connections that might be overlooked by human reviewers. This holistic approach enhances the quality and depth of research reviews, providing a solid foundation for further studies.

    Key AI Tools for Literature Screening

    Existing Tools and Features
    Several AI tools have gained popularity in the literature screening domain. These tools offer various features tailored to specific research needs and provide functionalities such as study deduplication, customizable screening criteria, and integration with reference management systems. However, it’s important to note that while these tools may enhance the efficiency of the systematic review process, they are not capable of offering full, end-to-end automation.

    These tools are designed to reduce the workload and time required for researchers to perform systematic reviews, but they primarily serve as aids to researchers rather than fully automated solutions. They help organize and manage the review process, ensuring that researchers can focus more on critical analysis and interpretation of the data. The current landscape of AI/ML literature screening tools is mostly based on supervised learning, indicating that complete end-to-end automation, until now, represented a goal rather than a reality. So far, these existing tools are mostly designed to assist students and researchers in performing tasks, without the capacity to perform the tasks for them. But now, at Loon, we pushed the boundaries of what’s possible and created Loon Hatch™.

    Antiquated AI/ML Methods vs. Cognitive Ensemble AI Systems™ with Agentic AI

    Traditional AI/ML Methods

    Traditional AI and machine learning (ML) methods have laid the foundation for current advancements in literature screening. Traditional AI/ML methods in literature screening involve the use of single-model algorithms that process data linearly. These antiquated methods often require substantial human oversight and frequent updates to maintain accuracy. In contrast, Cognitive Ensemble AI Systems™ with an agentic AI approach represent a significant advancement in the field. This innovative approach involves multiple AI agents working collaboratively to process and analyze literature, leveraging ensemble learning techniques to enhance accuracy and efficiency. By integrating various models and methods, Cognitive Ensemble AI Systems™ can dynamically adapt to new data and provide more reliable and comprehensive reviews. The agentic AI approach allows these systems to operate autonomously, significantly reducing the need for human intervention and enabling real-time updates and continuous improvement.

    Traditional AI/ML methods in literature screening involve the use of single-model algorithms that process data linearly. These methods primarily rely on supervised learning, where algorithms are trained on human-labelled data to identify patterns and make predictions. While effective, these methods require extensive manual intervention for data preparation and feature extraction, limiting their scalability and adaptability.

    Cognitive Ensemble AI Systems

    In contrast, bleeding-edge Cognitive Ensemble AI Systems™ represent a significant leap forward. These systems integrate multiple AI agents and models to leverage their collective strengths, improving accuracy and robustness. By combining various techniques, such as deep learning, reinforcement learning, and transfer learning, Cognitive Ensemble AI Systems™ can adapt to diverse datasets and complex patterns with minimal human intervention. This approach enhances the overall performance and scalability of AI literature screening tools.

    Agentic AI Approach

    The Agentic AI approach takes the AI evolution a step further by incorporating autonomous agents capable of making decisions and learning from their environment. These agents operate with a high degree of autonomy, continuously refining their algorithms based on real-time data and feedback. In literature screening, an Agentic AI can proactively search for new publications, evaluate their relevance, and integrate them into ongoing research workflows without constant supervision. This level of automation and intelligence represents the future of AI literature screening, promising unparalleled efficiency and accuracy.

    Applications in Various Fields

    Clinical Development, Market Access, and Health Technology Assessment
    Loon Hatch™ offers several use cases in these critical areas:

    • Value Demonstration: Comprehensive living systematic reviews continuously show the value of innovative therapies.
    • HTA and Regulatory Submissions: Streamline the preparation and drafting of submissions to HTA agencies.
    • Health Economic Modelling: No more assumptions, every input can be supported by an up-to-date systematic review.
    • Clinical Protocol Development: Base every choice on evidence for scientifically and regulatory sound clinical trial protocols.
    • Scientific Communication: Lead the scientific discourse in your relevant disease area with leadership in evidence synthesis.

    Medicine
    In the medical field, AI literature screening is used extensively for systematic reviews and meta-analyses. It helps clinicians and researchers stay updated with the latest findings, ensuring that medical practices are based on the most current evidence. Tools like the Market Access Forecaster assist in predicting and optimizing the pathway for new drugs to reach patients.

    Education
    Educational researchers use AI tools to screen literature for curriculum development, pedagogical strategies, and policy-making. The efficiency of AI allows educators to incorporate diverse perspectives and recent studies into their work.

    Social Sciences and Engineering
    In social sciences, AI literature screening aids in the exploration of complex societal issues by quickly synthesizing vast amounts of data. Engineers benefit from AI tools by staying abreast of technological advancements and innovative research.

    Challenges and Limitations

    High Costs and Model Updating
    Despite its advantages, AI literature screening faces challenges such as high computing costs and constant model updating. Ensuring the confidentiality of sensitive information and mitigating biases and hallucinations in AI algorithms are also critical to maintaining the integrity of research outcomes.

    Technical Barriers
    Technical barriers, including the need for robust computational infrastructure and expertise in AI technologies, can hinder the widespread adoption of AI literature screening. Addressing these barriers requires investment in technology and training.

    Innovations and Predictions
    The future of AI literature screening is bright, with continuous innovations expected in AI, machine learning and NLG. Emerging technologies like quantum computing and advanced neural networks hold the potential to further enhance the capabilities of AI in literature screening. A significant development in this field is the agentic AI approach, which involves multiple AI agents working collaboratively to improve the accuracy and efficiency of literature screening. This approach, exemplified by Loon’s Cognitive Ensemble AI Systems™ patent-pending technology, represents the latest innovation, offering a more dynamic and adaptive method for processing and analyzing vast amounts of research data.

    Implementing AI Literature Screening

    Steps and Best Practices
    Implementing AI literature screening involves several steps, including selecting the right tools, training the AI system, and continuously evaluating its performance. Best practices include regular updates to the AI model, ensuring data quality, and maintaining transparency in the screening process.

    Ethical Considerations

    Data Integrity and Accountability
    Ethical considerations are paramount in AI literature screening. Ensuring data integrity in AI processes and accountability for AI-driven decisions are essential to maintaining trust in AI technologies.

    Impact on Research Outcomes

    Quality and Speed of Research
    AI literature screening positively impacts research outcomes by enhancing the quality and speed of reviews. This technology enables researchers to produce more rigorous and timely studies, fostering collaboration and innovation.

    Comparing AI and Traditional Literature Screening

    Pros and Cons
    Comparing AI and traditional literature screening reveals distinct advantages and drawbacks. AI offers speed and accuracy but requires technical expertise, while traditional methods are more familiar but time-consuming and prone to human error. The AI agentic approach, however, mitigates these issues by automating the process and reducing the need for extensive human intervention. This approach ensures a higher degree of accuracy and efficiency, making it a superior alternative to traditional methods.

    Training and Development

    Skills Required and Resources
    To effectively create new AI literature screening tools, researchers need advanced skills in AI, data analysis, and computer science. Training programs and resources, such as online courses and workshops, are available to help researchers develop these skills, but developing robust skills takes time. Extensive training is also required to use the existing screening tools, as they depend on supervised learning and initial researcher screening of hundreds of articles before they can start their predictions, which don’t cover edge cases. But Loon Hatch™ requires no learning curve whatsoever, eliminating the opportunity cost and time researchers would waste on training outside their core specialties.

    AI Literature Screening in Academia

    Adoption and Impact
    Academia is increasingly adopting AI literature screening to enhance research efficiency. While some resistance exists due to concerns about reliability and job displacement, the overall impact has been positive, with many institutions reporting improved research outcomes.

    Regulatory and Policy Implications

    Compliance and Future Policies
    Regulatory and policy implications are critical for the future of AI literature screening. Ensuring compliance with data protection laws and developing guidelines for ethical AI use are essential for the responsible adoption of this technology.

    Open Source vs. Proprietary Tools

    Pros and Cons
    Choosing between open-source and proprietary AI literature screening tools involves weighing the pros and cons. Open-source tools offer flexibility and community support, while proprietary tools provide specialized features and dedicated customer service. Proprietary tools like Loon Hatch™ utilize proprietary technology to ensure maximum data privacy, offering maximum security and trust for sensitive sponsor data.

    Evaluating AI Literature Screening Tools

    Metrics and Reviews
    Evaluating AI literature screening tools involves assessing their performance using metrics such as accuracy, speed, and user satisfaction. Reviews from other researchers can provide valuable insights into the strengths and weaknesses of different tools. When evaluating tools, it is recommended to consider those utilizing agentic AI approaches and ensemble systems that integrate the latest AI/ML technologies. These advanced systems offer the best accuracy and efficiency by leveraging multiple AI agents to collaboratively process and analyze literature, ensuring the most comprehensive and up-to-date reviews.

    Conclusion and Future Outlook

    Summary and Predictions
    In conclusion, AI literature screening is revolutionizing the research landscape by enhancing efficiency, accuracy, and comprehensiveness. As the technology continues to evolve, researchers can expect even greater advancements that will further streamline the review process and improve research outcomes. The integration of tools like Loon Hatch™ offers a glimpse into the future of fully automated, end-to-end literature reviews. For those interested in staying at the forefront of research innovation, exploring these tools and incorporating them into their workflows will be essential.

    Free Your HEOR and Market Access Teams of Dull Tasks

    Researchers and institutions interested in harnessing the power of AI for literature screening are encouraged to explore the latest tools and technologies. Visit Loon’s website to learn more about our Cognitive Ensemble AI Systems™ and how we can enhance your research process. Embrace the future of research today and stay ahead in your field.