ASCO Presentation by UPenn on Human + AI vs. Human for Clinical Trial Pre-screening

ASCO Presentation by UPenn on Human + AI vs. Human for Clinical Trial Pre-screening

ASCO Presentation by UPenn on Human + AI vs. Human for Clinical Trial Pre-screening

Unlock the Future of Oncology Trial Prescreening with AI Manual chart reviews for oncology clinical trials are time-consuming and often inaccurate, leading to missed opportunities for patient enrollment. In a groundbreaking study funded by Mendel AI, researchers from the University of Pennsylvania’s Perelman School of Medicine evaluated how AI-powered natural language processing (NLP) can enhance clinical trial prescreening. Key findings from the study show that AI-assisted teams (Human+AI) achieved noninferior accuracy compared to traditional methods while significantly reducing review time per chart by nearly 10 minutes. The NLP system streamlined the identification of key eligibility criteria, improving efficiency without compromising accuracy. This cutting-edge research has major implications for accelerating clinical trial enrollment and improving access for eligible patients. Download the full presentation to explore the methodology, results, and impact of AI-driven prescreening by filling out the form below.

Transform Oncology Patient Records Into Actionable Insights

Transform Oncology Patient Records Into Actionable Insights

Transform Oncology Patient Records Into Actionable Insights

Revolutionizing Oncology with AI: Unlocking Critical Insights for Targeted Therapies The world of oncology is advancing at an unprecedented pace. Today’s success hinges on pinpointing highly specific patient cohorts—defined by biomarkers—and delivering precision treatments that yield optimal outcomes. Yet, extracting and interpreting the immense volume of patient data required to identify these cohorts remains a daunting obstacle for many healthcare organizations.In this eBook, discover how Mendel and Google Cloud are at the forefront of transforming cancer care through AI-driven solutions. By leveraging advanced analytics and machine learning, clinicians and researchers can gain actionable insights from patient records, accelerating the development and administration of life-saving, targeted therapies. In this eBook, discover how Mendel and Google Cloud are at the forefront of transforming cancer care through AI-driven solutions. By leveraging advanced analytics and machine learning, clinicians and researchers can gain actionable insights from patient records, accelerating the development and administration of life-saving, targeted therapies. Key Takeaways: 1. The intricacies of interpreting, managing, and leveraging oncology data 2. How AI empowers healthcare organizations to adopt a truly data-driven approach 3. How Mendel AI and Google Cloud are jointly redefining the oncology landscape 4. A real-world case study demonstrating how this innovative solution is empowering oncology professionals to improve patient outcomes Embark on a journey to understand how cutting-edge technology is reshaping cancer treatment and discover how your organization can harness AI to deliver precise, personalized care.

White Paper

Introduction to Hypercube’s Ontology and Reasoning Engine

Introduction to Hypercube’s Ontology and Reasoning Engine

Introduction to Hypercube’s Ontology and Reasoning Engine

Traditional medical ontologies are fragmented, static, and limit clinical reasoning capabilities. Mendel’s Hypercube Ontology and Reasoning Engine introduces a dynamic, reasoning-first framework that scales with medical knowledge. By breaking down data into foundational units and leveraging event-rooted reasoning, Mendel enables precise, efficient, and multi-dimensional insights across clinical workflows.

White Paper

Hypercube Analyst | From Complex Data to Clinical Action

Hypercube Analyst | From Complex Data to Clinical Action

Hypercube Analyst | From Complex Data to Clinical Action

Turning fragmented clinical data into actionable insights is critical for driving better patient outcomes. Mendel’s Hypercube Analyst simplifies the process by enabling precise, scalable, and efficient data exploration. With advanced query capabilities and seamless integration, teams can identify trends, extract value, and transform raw data into meaningful clinical actions.

White Paper

Hypercube Platform | Intelligence Layer for Clinical Data Analytics

Hypercube Platform | Intelligence Layer for Clinical Data Analytics

Hypercube Platform | Intelligence Layer for Clinical Data Analytics

Fragmented clinical data and outdated systems can limit healthcare insights and decision-making. Mendel’s Hypercube Platform uses advanced AI, hypergraph technology, and natural language querying to turn complex clinical data into actionable insights. This solution helps healthcare organizations streamline workflows, improve decision-making, and unlock the value of unstructured and structured data.

White Paper

Mendel AI for Registry Reporting

Mendel AI for Registry Reporting

Mendel AI for Registry Reporting

Clinical registry reporting often suffers from inefficiencies, time delays, and inconsistent data quality. Mendel’s AI copilot streamlines the process with automated workflows, improving accuracy and reducing the time required for case identification and data extraction. By leveraging AI-driven insights, teams achieve faster, higher-quality reporting with reduced manual effort.

White Paper

Hypercube Security, Compliance, and Deployment

Hypercube Security, Compliance, and Deployment

Hypercube Security, Compliance, and Deployment

Security, compliance, and deployment flexibility are critical when handling sensitive healthcare data. Mendel’s Hypercube platform ensures robust protection with HIPAA/GDPR compliance, encryption, and role-based access controls while offering scalable deployment options. This approach gives healthcare organizations the confidence to securely manage and analyze clinical data.

White Paper

Hypercube Analyst Implementation

Hypercube Analyst Implementation

Hypercube Analyst Implementation

Efficiently implementing advanced analytics tools is essential for managing complex healthcare data. Mendel’s Hypercube Analyst Implementation provides a streamlined approach, offering SQL compatibility, distributed querying, and ETL pipeline integration. This solution ensures high performance, reduced complexity, and faster insights across large clinical datasets.

White Paper

Improving Clinical Trial Participant Prescreening With Artificial Intelligence (AI): A Comparison of the Results of AI Assisted vs Standard Methods in 3 Oncology Trials

Improving Clinical Trial Participant Prescreening With Artificial Intelligence (AI): A Comparison of the Results of AI Assisted vs Standard Methods in 3 Oncology Trials

Improving Clinical Trial Participant Prescreening With Artificial Intelligence (AI): A Comparison of the Results of AI Assisted vs Standard Methods in 3 Oncology Trials

Delays in clinical trial enrollment and difficulties enrolling representative samples continue to vex sponsors, sites, and patient populations. Here we investigated use of an artificial intelligence-powered technology, Mendel.ai, as a means of overcoming bottlenecks and potential biases associated with standard patient prescreening processes in an oncology setting.

White Paper

Mendel Unveils Groundbreaking Neuro-Symbolic AI System Outperforming GPT-4 for Automatic Cohort Retreival in New Study

Mendel Unveils Groundbreaking Neuro-Symbolic AI System Outperforming GPT-4 for Automatic Cohort Retreival in New Study

Mendel Unveils Groundbreaking Neuro-Symbolic AI System Outperforming GPT-4 for Automatic Cohort Retreival in New Study

“Our latest research at Mendel marks a significant milestone in the field of AI in general, and healthcare in particular,” said Wael Salloum, Cofounder and Chief Science Officer at Mendel. “We are the leader in clinical reasoning by coupling LLMs with our hypergraph reasoning, enhancing both the effectiveness and efficiency of patient cohort retrieval.

Transforming Unstructured Pathology Data

Transforming Unstructured Pathology Data

Transforming Unstructured Pathology Data

A leading diagnostics testing company faced significant challenges in managing 200 million unstructured pathology reports annually, leading to inefficiencies and scalability issues. Their goal was to enhance operational efficiency and transform unstructured data into actionable insights for oncology-related treatments and research. Mendel's HyperCube Platform, introduced through a pilot program, achieved a 25-35% increase in precision and recall over traditional methods, raising the value per slide from $1 to $3, and ensuring data security with seamless Snowflake integration. The platform empowered business users with intuitive data querying, reducing the analytics team's workload. The pilot demonstrated significant improvements, with Mendel achieving higher precision and recall rates compared to the company's existing methods. Mendel's HyperCube platform stands as a crucial tool for translating clinical data into meaningful insights, driving enhanced patient outcomes and scientific discovery.

White Paper

Coupling Symbolic Reasoning with Language Modeling for Efficient Longitudinal Understanding of Unstructured Electronic Medical Records

Coupling Symbolic Reasoning with Language Modeling for Efficient Longitudinal Understanding of Unstructured Electronic Medical Records

Coupling Symbolic Reasoning with Language Modeling for Efficient Longitudinal Understanding of Unstructured Electronic Medical Records

The application of Artificial Intelligence (AI) in healthcare has been revolutionary, especially with the recent advancements in transformer-based Large Language Models (LLMs). However, the task of understanding unstructured electronic medical records remains a challenge given the nature of the records (e.g., disorganization, inconsistency, and redundancy) and the inability of LLMs to derive reasoning paradigms that allow for comprehensive understanding of medical variables. In this work, we examine the power of coupling symbolic reasoning with language modeling toward improved understanding of unstructured clinical texts. We show that such a combination improves the extraction of several medical variables from unstructured records. In addition, we show that the state-of-the-art commercially-free LLMs enjoy retrieval capabilities comparable to those provided by their commercial counterparts. Finally, we elaborate on the need for LLM steering through the application of symbolic reasoning as the exclusive use of LLMs results in the lowest performance.