Stat Trials Pulse FAQs

Frequently Asked Questions (FAQ)

What is STAT Trials Pulse powered by Applied XL?

STAT Trials Pulse is a clinical trials intelligence platform that uses machine learning and editorial algorithms to monitor clinical trials, scientific papers, and company announcements, turning unstructured data into actionable trends and insights. The platform delivers contextual, real-time alerts by detecting noteworthy shifts in publicly available data.

For a full overview of the product features, please visit our user guide.

Who uses STAT Trials Pulse?

STAT Trials Pulse is used by life sciences professionals at some of the largest pharma organizations, emerging biotech companies and hedge funds. The platform caters to individuals who often work in areas related to competitive intelligence, strategy, business development, portfolio analysis, strategic investment, and clinical development.

How is the platform being used?

STAT Trials Pulse is being used by life sciences professionals to accelerate decision-making on partnerships, investments, regulatory strategy, competitive positioning and commercialization activities.

Our customers are already experiencing the impact of STAT Trials Pulse. With it, they have:

Adjusted commercialization timelines by tracking changes in competing clinical trials.
Defined R&D strategy by following the latest clinical activity from academic institutions and emerging biotech companies.
Optimized clinical trial design by monitoring the roadblocks that have impacted new drug development in the same therapeutic area.
Adjusted regulatory strategy by getting early signals on the shortcomings of comparable trials.
Prioritized investment opportunities by identifying emerging therapeutic areas and interventions and getting outcomes indications before official news is released.

What are the key features of STAT Trials Pulse?

A personalized experience: build dynamic feeds by selecting conditions, interventions, and organizations; refine by events types (trials that have stopped early, changed enrollment, had a recent press release, etc.)and set parameters (organization type, purpose, phase, current status) to curate an experience tailored to the information you need to make decisions.
Detection of noteworthy events: editorial algorithms and machine learning automatically detect and classify important state changes in clinical trials data to summarize the nature of a given occurrence.
Trends across the clinical landscape: monitor trends and insights in the clinical space that aggregate proprietary event data and surface otherwise undetectable shifts in clinical trial events based on outliers, anomalies, and aggregate patterns.
Context around trial events: contextualize trials data with a visual timeline that lets you see state changes, key milestones, and any deviations to the study’s expected trajectory.
Editorially curated collections: explore the clinical trials landscape through the eyes of an expert. Follow featured feeds editorially selected around relevant topics by your favorite STAT journalists and the AXL expert team.
Smart alerts: get notified of noteworthy changes when studies stop early, are delayed, update completion dates, experience shifts in enrollment, when results are available and more.

What new features can I anticipate in the near future?

We are working on a number of new features that we are excited to release in the coming weeks and months. Some of these capabilities include:

A fully optimized mobile experience.
New alert types including changes to end points, new sites being added or removed, and patient inclusion/exclusion criteria.
Profile pages for interventions, organizations and
Charts, visualizations, and flashcards integrated on the trials detail page, to inform you of the relative importance of a certain trial/program to an organization, or the phase distribution of a specific intervention.
Integration with new data from FDA and earnings call transcripts.
A personalized email briefing sent to you on a weekly basis with the most important updates across the areas you care about.
Profile pages at the topic level with calculations, visualizations, and context to give you greater insight into the changing landscapes of conditions, interventions, and organizations.
Time series visualizations in The Pulse page to provide context around event outliers and other important occurrences.

You can help us prioritize our roadmap by completing this brief survey.

Can I schedule a demo with your team to get a better idea of how to use the tool?

Yes! We host webinars and demos, but we are also happy to guide you in a private demo, which you can schedule here.

Do you have a user guide for the platform?

You can consult our STAT Trials Pulse’s full user guide here. The document explains how all features work and is updated as we release new functionality.

What are the pricing options for a subscription to STAT Trials Pulse?

All users may enjoy a 4 week free trial when they first sign up for STAT Trials Pulse, no strings attached, and no credit card information required.

Users may then transition to an Individual Subscription, which is currently offered as a limited time introductory offer of $125/month billed annually or $170/month billed quarterly. STAT+ subscribers unlock 15% off an annual membership.

We offer discounted rates for groups, companies, and organizations. If you think this may be of interest to your organization, please schedule a brief meeting with us here.

Who created STAT Trials Pulse ?

STAT News and Applied XL have partnered to bring you STAT Trials Pulse. Applied XL brings to the table an experienced team of computational journalists and engineers that specialize in real-time information processing. STAT builds on its track record of telling compelling stories in health and medicine to inform their clinical trials algorithm. By combining the precision of data science with the high standards of journalism, we’ve unlocked a powerful new way to surface the most relevant updates in the clinical trials space.

Why was this product launched?

In March 2020, Applied XL and STATNews joined forces to track Covid-19 by aggregating multiple data sources from around the world and making it available through a dashboard that has since received over 2.7 million visits. Seeing first hand the impact of this effort, the two teams developed a plan to monitor not only the disease but the new treatment landscape for Covid -- initially taking the form of a data investigation authored by senior writer Matt Herper and Applied XL’s Erin Riglin.

“Being able to visualize and track the data embedded deep in clinicaltrials.gov gave me a whole new perspective on what we could learn from this resource that I’d used for so many years,” Herper said. “It was clear that there was a resource here that could be useful to scientists, businesspeople, investors and journalists.”

We interviewed over 65 life sciences professionals and surveyed hundreds more to understand their information needs. The biggest takeaway: professionals in this space are overwhelmed with unstructured clinical trials data; and as a result, they miss out on critical information that they need to do their jobs. In fact, they spend almost 75% of their time looking for data, and only 25% of their time making sense of that information to make decisions. With our background in computational journalism, we knew we could build a tool that would change this — that is, one that would do the heavy lifting of finding and contextualizing the data for these professionals, so they could focus on the work that really matters.

As one of our users put it, “Surfacing what other companies are doing can save us half of the time. This extra time can be used to spend on implications to business and readjusting our timelines.”

How does STAT Trials Pulse work?

STAT Trials Pulse uses machine learning and natural language processing algorithms to detect and make sense of millions of data points in the clinical trials space. The algorithms are then fine tuned through input by journalists and other life science experts, reflecting our commitment to responsible AI and high algorithmic standards. The result combines cutting-edge data science techniques with editorial principles, providing you with objective, fast, and reliable information.

The system navigates the infoscape for life sciences data and consciously detects what's new and noteworthy.

We monitor and structure all data from clinicaltrials.gov, PubMed, and press releases.
Our algorithms are encoded with prioritization and editorial labeling frameworks that have been developed by a network of in-industry experts, including STAT journalists, that help surface important signals and de-prioritize noise.
The product minimizes setup and increases the relevance of the information users receive, helping us to flag the most important shifts in the trials they’re watching. However, the full feed of data is always available for the end user to explore in depth.

How are editorial classification labels developed and what insight do they provide?

Rather than taking a snapshot view of clinical trials, we track thousands of daily changes across multiple data sources to find the most crucial updates. Each of those events are classified and ranked by noteworthy criteria defined by STAT journalists and other expert sources.

By deriving and aggregating proprietary events and continuously looking at these new data points longitudinally, event detection algorithms are able to surface trends that provide an up-to-date view of emerging activity that others may miss.

“The new tool gathers vital information and context on clinical trials far more efficiently than I can do myself — and the algorithm’s ability to surface otherwise invisible trends is truly remarkable,” said STAT News Kate Sheridan, one of the journalists who contributed to the effort.

For example, consider these two trials, both with recent status updates to 'Recruiting':

You’ll see that the update to the same status in these trials received two different classifications. That’s due to the editorial considerations of the trials’ patterns.

The first trial, experiencing a ‘Recruitment Strategy’ event, changed from ‘Enrolling by Invitation’ to ‘Recruiting.’ A change from a specific, invitation-based strategy to a broader, more general recruiting strategy may indicate that the trial is struggling with enrollment goals, or that they've expanded their intended population to a larger group.

The second trial, experiencing a ‘Re-Entering Recruitment’ event, changed from ‘Active, not recruiting’ to ‘Recruiting.’ This may indicate that thus far, the data collected isn’t substantive to prove statistically significant efficacy, so in hopes of improving these metrics, the trial is enrolling an increased number of patients.

This is how we use aggregate patterns to assign editorial labels. Furthermore, we can mine unstructured data from clinical trial events to assign classification. For example, a trial stopping early can have different implications based on the reason it stopped:

Once we’ve defined the parameters of an editorial classification or signal to be surfaced, the models are trained to detect and classify these editorial definitions at scale on an ongoing basis.

‍

How are editorial frameworks implemented at scale with real-time data?

How do we assign these labels on a consistent and reliable basis as new data comes in each day? Machine learning algorithms. We train our algorithms on domain-specific datasets through an iterative process with our expert network, so the algorithm can identify the nuances of events and their context in the landscape.

We strongly believe in transparency and human involvement in the implementation of artificial intelligence. For that reason, you’ll be seeing this new icon around the tool whenever something is machine-generated:

As part of the ongoing process of accuracy-training our algorithms and providing the ever-important human touch to AI, you will always have the opportunity to provide feedback on machine-generated classification. This will increase the accuracy of the system as well as better personalize the curation of your experience on the tool.

How is STAT Trials Pulse different from other clinical trials data or service providers?

Think of us as a Twitter to other service providers’ Google. While other products provide the most data possible through search tools, we are focused on real-time event detection for life sciences. We want to help you surface what’s new and noteworthy and discover information that you may not know to explicitly search. We have optimized the workstream of diligence via search by creating editorial frameworks for prioritization and providing additional, proprietary context. We’ve also optimized the workstream of discovery by using natural language processing for document recommendation and surfacing trends and insights in the clinical landscape, both globally and tailored specifically to your interests.

We believe it is important to provide an optimized information filtering system on clinical trials data. STAT Trials Pulse aims to generate high quality insights at scale, with unparalleled relevance and speed. Our product provides a tailored experience to each user that does not require a time-consuming set up process or costly analyst hours.

Additionally, our event classification system is completely unique. The ability to filter on specific events a trial may be experiencing is one you cannot find elsewhere. Furthermore, this proprietary event classification allows us to surface trends in the clinical landscape that otherwise go undetected in search-based tools.

How are you able to personalize information for each user?

Applied XL’s system uses hundreds of attributes, known as tags, to classify clinical trials. Each tag corresponds to specific characteristics of the trial: for example, the type of intervention, the therapeutic area, the targets, the enrollment count, and the semantics used to describe those studies.

Our algorithms assess the similarity of clinical trials based on a combination of publicly available data and proprietary tags. These trials are prioritized based on the resulting similarity scores, recency, and impact. This enables rapid discovery of similar trials across a variety of filtered categories: trials from the same company, trials from other companies, trials focused on similar diseases, etc.

How can I help improve the platform?

You can send us your feedback to support@appliedxl.com or by completing this survey. Tell us what features or data you’d like to have access to in the future, as well as any thoughts or questions about the product you may have.

You can also help enrich the accuracy of our algorithms and classifications through discrete data labeling challenges that you will see integrated throughout the platform.

How do Smart Alerts work?

Create feeds and follow trials to activate smart alerts that notify you of state changes, key milestones, and any deviations to the expected trajectory, along with explanatory context.
Feeds you’ve created and trials you’ve followed can be managed in your Library on the left hand navigation bar.

How do Email Briefings work?

Personalized digest delivered to your inbox. Select daily or weekly recap emails to receive the latest updates in your corner of the clinical trial landscape.
You can set the frequency at which you receive email briefings by clicking the Notification Settings’ in your profile.

Data and Algorithmic Transparency Disclosure

What are your primary sources of data?

STAT Trials Pulse leverages data from ClinicalTrials.gov which is processed and updated such that it is current at all times. We highlight when the content of the data is modified, and also provide a complete description of those modifications. The clinical trials data currently used in STAT Trials Pulse is exclusively from interventional studies.

This platform also uses publicly available data courtesy of the U.S. National Library of Medicine (NLM), the National Institutes of Health, and the Department of Health and Human Services. Please note that NLM is not responsible for the product and does not endorse or recommend this or any other product.

We also monitor and incorporate data from press releases from thousands of companies made available to use via the Associated Press.

Disclaimer: Applied XL does not warrant or assume any legal liability or responsibility for the accuracy, completeness, or usefulness of any information or data disclosed.

How do you monitor the quality of your algorithms?

All algorithms are vetted and validated by humans who are experts in their fields. Exploration of data is performed by using computational journalism methods to help us identify any eventual errors, biases, and areas for further refinement.

During model training, we ensure that enough data has been provided to the algorithm to account for unusual or edge cases. A network of curated experts, including STAT journalists and researchers, help us evaluate outliers that are flagged by our system. This feedback is used to recalibrate models, or to verify the accuracy of important events. Furthermore, the human-in-the-loop technology integrated in our platform allows for continuous feedback that improves our algorithms on an ongoing basis.

Classifications that are algorithmically generated always include a disclosure to provide transparency and visibility into the process. These disclosures also offer the opportunity for the user to provide feedback so we can reassess our current models. Experts and users can contribute with this discrete data feedback, which is used to retain our machine learning algorithms to achieve increased levels of precision and to help control data drift. We leverage strategic human input to surface new labels that did not previously exist, ensuring a dynamic and editorially sound classification model.

Disclaimer: Although we follow all the necessary steps to constantly ensure quality of algorithmically-generated information, there may be occurrences where that information is not accurate. The content available through our platform is designed for educational and informational purposes and is not construed to be advice of any kind. You should not rely on information available in or via the services as a substitute for professional advice, including medical advice. You must not rely on any of the content and information for any purposes whatsoever, and you must seek your own independent professional advice before relying on or otherwise deciding to take any action on the basis of any content or information available through the services.

STAT Trials Pulse uses machine learning to sort through millions of clinical trial events in real-time to surface the ones that are most relevant to you.

Frequently Asked Questions (FAQ)

Data and Algorithmic Transparency Disclosure

Access Our Data