Transforming Industries with MongoDB and AI: Healthcare

Francesc Mateu Amengual
April 22, 2024 | Updated: August 8, 2024
#AI in Industries

This is the sixth in a six-part series focusing on critical AI use cases across several industries. The series covers the manufacturing and motion, financial services, retail, telecommunications and media, insurance, and healthcare industries.

In healthcare, transforming data into actionable insights is vital for enhancing clinical outcomes and advancing patient care. From medical professionals improving care delivery to administrators optimizing workflows and researchers advancing knowledge, data is the lifeblood of the healthcare ecosystem. Today, AI emerges as a pivotal technology, with the potential to enhance decision-making, improve patient experiences, and streamline operations — and to do so more efficiently than traditional systems.

Patient experience and engagement

While they may not expect it based on past experiences, patients crave a seamless experience with healthcare providers. Ideally, patient data from healthcare services, including telehealth platforms, patient portals, wearable devices, and EHR, can be shared – securely – across interoperable channels. Unfortunately, disparate data sources, burdensome and time-consuming administrative work for providers, and overly complex and bloated solution stacks at the health system level all stand in the way of that friction-free experience.

AI can synthesize vast amounts of data and provide actionable insights, leading to personalized and proactive patient care, automated administrative processes, and real-time health insights. AI technologies, such as machine learning algorithms, natural language processing, and chatbots, are being used to enhance and quantify interactions. Additionally, AI-powered systems can automatically schedule appointments, send notifications, and optimize clinic schedules, all reducing wait times for patients. AI-enabled chatbots and virtual health assistants provide 24/7 support, offering instant responses, medication reminders, and personalized health education. AI can even identify trends and predict health events, allowing for early intervention and reduction in adverse outcomes.

MongoDB’s flexible data model can unify disparate data sources, providing a single view of the patient that integrates EHRs, wearable data, and patient-generated health data for personalized care and better patient outcomes. For wearables and medical devices, MongoDB is the ideal underlying data platform to house time series data, significantly cutting down on storage costs while enhancing performance. With Atlas for the Edge, synchronization with edge applications, including hospital-at-home setups, becomes seamless.

On the patient care front, MongoDB can support AI-driven recommendations for personalized patient education and engagement based on the analysis of individual health records and engagement patterns, and Vector Search can power search functionalities within patient portals, allowing patients to easily find relevant information and resources, thereby improving the self-service experience.

Enhanced clinical decision making

Healthcare decision-making is critically dependent on the ability to aggregate, analyze, and act on an exponentially growing volume of data. From EHRs and imaging studies to genomic data and wearable device data, the challenge is not just the sheer volume but the diversity and complexity of data. Healthcare professionals need to synthesize information across various dimensions to make informed, real-time, accurate decisions. Interoperability issues, data silos, lack of data quality, and the manual effort required to integrate and interpret this data all stand in the way of better decision-making processes.

The advent of AI technologies, particularly NLP and LLMs, offers transformative potential for healthcare decision-making by automating the extraction and analysis of data from disparate sources, including structured data in EHRs and unstructured text in medical literature or patient notes. By enabling the querying of databases using natural language, clinicians can access and integrate patient information more rapidly and accurately, enhancing diagnostic precision and personalizing treatment approaches. Moreover, AI can support real-time decision-making by analyzing streaming data from wearable devices, alerting healthcare providers to changes in patient conditions that require immediate attention.

MongoDB, with its flexible data model and powerful data development platform, is uniquely positioned to support the complex data needs of healthcare decision-making applications. It can seamlessly integrate diverse data types, from FHIR-formatted clinical data to unstructured text and real-time sensor data, in a single platform. By integrating MongoDB with Large Language Models (LLMs), healthcare organizations can create intuitive, AI-enhanced interfaces for data retrieval and analysis. This integration not only reduces the cognitive load on clinicians but also enables them to access and interpret patient data more efficiently, focusing their efforts on patient care rather than navigating complex data systems. MongoDB's scalability ensures that healthcare organizations can manage growing data volumes efficiently, supporting the implementation of AI-driven decision support systems. These systems analyze patient data in real-time against extensive medical knowledge bases, providing clinicians with actionable insights and recommendations, thereby enhancing the quality and timeliness of care provided.

MongoDB's Vector Search further enriches decision-making processes by enabling semantic search across vast datasets directly within the database. This integrated approach enables the application of pre-filters based on extensive metadata, enhancing the efficiency and relevance of search results without the need to synchronize with dedicated search engines or vector stores, meaning healthcare professionals can utilize previously undiscoverable insights, streamlining the identification of relevant information and patterns.

Clinical trials and precision medicine

The need for innovation and transformation isn’t just limited to the patient-provider-healthcare system experience. The challenges of conducting clinical trials and advancing precision medicine are significant, from identifying and enrolling suitable participants to data management practices are fraught with the potential for errors, compromising the accuracy and reliability of trial outcomes. Moreover, the traditional one-size-fits-all approach to treatment development fails to address the unique genetic makeup of individual patients, limiting the effectiveness of therapeutic interventions.

AI can make clinical trials faster and treatments more personalized. It's like having a super-smart assistant that can quickly find the right people for studies, keep track of all the data without making mistakes, and even predict which medicines will work best for different people. This means doctors can create safe, efficient treatments that fit you perfectly, just like a tailor-made suit. Plus, with AI's help, these custom treatments can be developed quicker and be more affordable, bringing us closer to a future where everyone gets the care they need, designed just for them. It's a big step towards making medicine not just about treating sickness but about creating health plans that are as unique as patients are.

MongoDB plays a pivotal role in modernizing clinical trials and advancing precision medicine by addressing complex data challenges. Its flexible data model excels in integrating diverse data types, from EHRs and genomic data to real-time patient monitoring streams. This capability is crucial for clinical trials and precision medicine, where combining various data sources is necessary, sometimes through a project purpose ODL, to develop a comprehensive understanding of patient health and treatment responses.

For clinical trials, MongoDB can streamline participant selection by efficiently managing and querying vast datasets to identify candidates who meet specific criteria, significantly reducing the recruitment time. Its ability to handle large-scale, complex datasets in real-time also facilitates the dynamic monitoring of trial participants, enhancing the safety and accuracy of trials.

Other notable use cases

  • Patient Flow Optimization and Emergency Department Efficiency: AI algorithms can process historical and real-time data to forecast patient volumes, predict bed availability, and identify optimal staffing levels, enabling proactive resource allocation and patient routing.

  • Virtual Health Assistants for Chronic Disease Management: Utilizing AI-powered virtual assistants to monitor patients' health status, provide personalized advice, and support medication adherence for chronic conditions such as diabetes and hypertension.

  • AI-Enhanced Digital Pathology and Medical Imaging: Build modern VNA (Vendor Neutral Archive and Digital pathology solutions with innovative approaches, dealing with interoperable data, and manage extensive metadata associated with all your resources enabling fast findings and automated annotations.

  • Operational Efficiency in Hospital Resource Management: Implementing AI to optimize hospital operations, from staff scheduling to inventory management, ensuring resources are used efficiently and patient care is prioritized.

Learn more about AI use cases for top industries in our new ebook, How Leading Industries are Transforming with AI and MongoDB Atlas.

Head over to our quick-start guide to get started with Atlas Vector Search today.

← Previous

Retrieval Augmented Generation for Claim Processing: Combining MongoDB Atlas Vector Search and Large Language Models

Following up on our previous blog, AI, Vectors, and the Future of Claims Processing: Why Insurance Needs to Understand The Power of Vector Databases , we’ll pick up the conversation right where we left it. We discussed extensively how Atlas Vector Search can benefit the claim process in insurance and briefly covered Retrieval Augmented Generation (RAG) and Large Language Models (LLMs). Check out our AI resource page to learn more about building AI-powered apps with MongoDB. One of the biggest challenges for claim adjusters is pulling and aggregating information from disparate systems and diverse data formats. PDFs of policy guidelines might be stored in a content-sharing platform, customer information locked in a legacy CRM, and claim-related pictures and voice reports in yet another tool. All of this data is not just fragmented across siloed sources and hard to find but also in formats that have been historically nearly impossible to index with traditional methods. Over the years, insurance companies have accumulated terabytes of unstructured data in their data stores but have failed to capitalize on the possibility of accessing and leveraging it to uncover business insights, deliver better customer experiences, and streamline operations. Some of our customers even admit they’re not fully aware of all the data in their archives. There’s a tremendous opportunity to leverage this unstructured data to benefit the insurer and its customers. Our image search post covered part of the solution to these challenges, opening the door to working more easily with unstructured data. RAG takes it a step further, integrating Atlas Vector Search and LLMs, thus allowing insurers to go beyond the limitations of baseline foundational models, making them context-aware by feeding them proprietary data. Figure 1 shows how the interaction works in practice: through a chat prompt, we can ask questions to the system, and the LLM returns answers to the user and shows what references it used to retrieve the information contained in the response. Great! We’ve got a nice UI, but how can we build an RAG application? Let’s open the hood and see what’s in it! Figure 1: UI of the claim adjuster RAG-powered chatbot Architecture and flow Before we start building our application, we need to ensure that our data is easily accessible and in one secure place. Operational Data Layers (ODLs) are the recommended pattern for wrangling data to create single views. This post walks the reader through the process of modernizing insurance data models with Relational Migrator, helping insurers migrate off legacy systems to create ODLs. Once the data is organized in our MongoDB collections and ready to be consumed, we can start architecting our solution. Building upon the schema developed in the image search post , we augment our documents by adding a few fields that will allow adjusters to ask more complex questions about the data and solve harder business challenges, such as resolving a claim in a fraction of the time with increased accuracy. Figure 2 shows the resulting document with two highlighted fields, “claimDescription” and its vector representation, “claimDescriptionEmbedding” . We can now create a Vector Search index on this array, a key step to facilitate retrieving the information fed to the LLM. Figure 2: document schema of the claim collection, the highlighted fields are used to retrieve the data that will be passed as context to the LLM Having prepared our data, building the RAG interaction is straightforward; refer to this GitHub repository for the implementation details. Here, we’ll just discuss the high-level architecture and the data flow, as shown in Figure 3 below: The user enters the prompt, a question in natural language. The prompt is vectorized and sent to Atlas Vector Search; similar documents are retrieved. The prompt and the retrieved documents are passed to the LLM as context. The LLM produces an answer to the user (in natural language), considering the context and the prompt. Figure 3: RAG architecture and interaction flow It is important to note how the semantics of the question are preserved throughout the different steps. The reference to “adverse weather” related accidents in the prompt is captured and passed to Atlas Vector Search, which surfaces claim documents whose claim description relates to similar concepts (e.g., rain) without needing to mention them explicitly. Finally, the LLM consumes the relevant documents to produce a context-aware question referencing rain, hail, and fire, as we’d expect based on the user's initial question. So what? To sum it all up, what’s the benefit of combining Atlas Vector Search and LLMs in a Claim Processing RAG application? Speed and accuracy: Having the data centrally organized and ready to be consumed by LLMs, adjusters can find all the necessary information in a fraction of the time. Flexibility: LLMs can answer a wide spectrum of questions, meaning applications require less upfront system design. There is no need to build custom APIs for each piece of information you’re trying to retrieve; just ask the LLM to do it for you. Natural interaction: Applications can be interrogated in plain English without programming skills or system training. Data accessibility: Insurers can finally leverage and explore unstructured data that was previously hard to access. Not just claim processing The same data model and architecture can serve additional personas and use cases within the organization: Customer Service: Operators can quickly pull customer data and answer complex questions without navigating different systems. For example, “Summarize this customer's past interactions,” “What coverages does this customer have?” or “What coverages can I recommend to this customer?” Customer self-service: Simplify your members’ experience by enabling them to ask questions themselves. For example, “My apartment is flooded. Am I covered?” or “How long do windshield repairs take on average?” Underwriting: Underwriters can quickly aggregate and summarize information, providing quotes in a fraction of the time. For example, “Summarize this customer claim history.” “I Am renewing a customer policy. What are the customer's current coverages? Pull everything related to the policy entity/customer. I need to get baseline info. Find relevant underwriting guidelines.” If you would like to discover more about Converged AI and Application Data Stores with MongoDB, take a look at the following resources: RAG for claim processing GitHub repository From Relational Databases to AI: An Insurance Data Modernization Journey Modernize your insurance data models with MongoDB and Relational Migrator Head over to our quick-start guide to get started with Atlas Vector Search today.

April 18, 2024
Next →

MongoDB and Partners: Building the AI Future, Together

If you’re like me, over the past year you’ve closely watched AI’s developments—and the world’s reactions to them. From infectious excitement about AI’s capabilities, to impatience with its cost and return on investment, every day has been filled with AI twists and turns. It’s been quite the roller coaster. During the ride, from time to time I’ve wondered where AI falls on the Gartner hype cycle, which gives "a view of how a technology or application will evolve over time." Have we hit the "peak of inflated expectations" only to fall into the "trough of disillusionment?" Or is the hype cycle an imperfect guide, as The Economist argues? The reality is that it takes time for any new technology—even transformative ones like AI—to take hold. And every advance, no matter how big, has had its detractors. A famous example is that of Picasso (!), who in 1968 said, “Computers are useless. They can only give you answers.” (!!) For our part, MongoDB is convinced that AI is a once-in-a-generation technology that will enhance every future application—a belief that has been reinforced by the incredible work our partners have shared at MongoDB’s 2024 events. Speeding AI development MongoDB is committed to helping organizations of all sizes succeed with AI, and one way we’re doing that is by collaborating with the MongoDB partner ecosystem to create powerful, user-friendly AI development tools and solutions. For example, Fireworks.ai —which is a member of the MongoDB AI Applications Program ecosystem —created an inference solution that hosts gen AI models and supports containerized deployments. This tool makes it easier for developers to build and deploy powerful applications with a range of easy-to-use tools and customization options. They can choose to use state-of-the-art, open-source language, image, and multimodal foundation models off the shelf, or they can customize and fine-tune models to their needs. Jointly, Fireworks.ai and MongoDB provide a solution for developers who want to leverage highly curated and optimized open-source models and combine these with their organization’s own proprietary data—and to do so with unparalleled speed and security. “MongoDB is one of the most sophisticated database providers, and it’s very easy to use,” said Benny Chen , cofounder of Fireworks.ai. "We want developers to be able to use these tools, and we want to work with providers who enable and empower developers." Nomic , another MAAP ecosystem member, also enables developers with best-in-class solutions across the entire unstructured data workflow. Their Embed offering, available through the Nomic API , allows users to vectorize large-scale datasets for use in text, image, and multimodal retrieval applications, including retrieval-augmented generation (RAG), using only their web browser. The Nomic-MongoDB solution is a highly efficient, open-weight model that developers can use to visualize the unstructured datasets they store in MongoDB Atlas . These insights help users quickly discover trends and articulate data-driven value propositions. Nomic also supported the recently announced vector quantization in MongoDB Atlas Vector Search , which reduces vector sizes while preserving performance. Last—but hardly least!—there’s our new reference architecture with MAAP partners AWS and Anthropic. Announced at MongoDB.local London , the reference architecture supports building memory-enhanced AI agents, and is designed to streamline complex processes and develop smarter, more responsive applications. For more—including a link to the code on Github— check out the MongoDB Developer Center . Making AI work for anyone and everyone The companies MongoDB partners with aren’t just making gen AI easier for developers—they’re building tools for everyone. For example, Capgemini has invested $2 billion in gen AI and is training 100,000 of its employees in the technology. GenYoda, a solution that helps insurance professionals with their daily work, is a product of this investment. GenYoda leverages MongoDB Atlas Vector Search to analyze large amounts of customer data, like policy statements, premiums, claims history, and health information. Using GenYoda, insurance professionals can quickly analyze underwriters’ reports to make informed decisions, create longitudinal health summaries, and streamline customer interactions to improve contact center efficiency. GenYoda can ingest 100,000 documents in just a few hours and respond to users’ queries in two to three seconds—a metric on par with the most widely used gen AI models. And it produces results: in one example, by using Capgemini’s solution an insurer was able to increase productivity by 15%, add new reports 25% faster (thus speeding decision-making), and reduce the manual effort of searching PDFs, increasing efficiency by 10%. Building the future of AI together So, what’s next? Honestly, I’m as curious as you are. But I’m also incredibly excited. At MongoDB, we’re active participants in the AI revolution, working to embrace the possibilities that lie ahead. The future of gen AI is bright, and I can’t wait to see what we’ll build together. To learn more about how MongoDB can accelerate your AI journey, explore the MongoDB AI Applications Program .

November 4, 2024