CAMBRIDGE, MA - AUGUST 14, 2026 - In litigation, every fact matters. But those facts rarely live in one clean place. They are spread across medical records, reports, exhibits, charts, tables, images, handwritten notes, and thousands of pages of case material.
Chatbots are good at giving you an answer. But, finding every fact is a different problem. Research shows that language models can miss information buried in long inputs, andreal-world studies of medical records have found omissions even when the source information was available to the model.
That’s why we built Fact Extraction on newcase.ai.
Tell newcase.ai which data points you need, and Fact Extraction reviews every page of the record to find them. Including facts inside tables, images, charts, handwritten notes, and other unstructured data.
The results come back in one structured table, with every value linked to its source document and page. When the system is not confident about an entry, it flags it for your review instead of quietly filling in the gap.
Here are ways litigation teams can put it to work.
Example 1: Track Lab Values Across Thousands of Pages
A single lab value is easy to find. Finding every instance of that value across years of treatment is not.
With Fact Extraction, you can ask for specific values such as, glucose, hemoglobin, creatinine, blood pressure, or any other data point, and pull every relevant result into one table, organized by date, provider, lab, or any other data point you want to cross-reference with.
You can then visualize the values over time to see changes, spikes, gaps, and patterns that are difficult to notice while reviewing records page by page.
And because every value links back to the source, you can move from the chart to the underlying record whenever something deserves a closer look.
When you need to understand those findings as part of the patient's broader treatment history, use a Medical Chronology to see them alongside diagnoses, procedures, medications, visits, and other medical events.
Example 2: Follow Medication and Treatment Changes
Treatment histories are rarely documented in one place. A medication may appear in a physician note, change in a discharge summary, disappear from a medication list, and then show up again months later.
Fact Extraction can pull the fields you need across the entire record: medication name, dose, start date, stop date, changes in dosage, reason for the change, prescribing physician, or other case-specific details.
Instead of manually building a spreadsheet from hundreds of documents, you get one structured view of the treatment history.
If an entry is difficult to read or the source is unclear, the system flags it for review. The expert stays in the loop for the facts that actually require judgment.
Example 3: Compare What the Records Say With What the Witness Said
Fact Extraction can pull the dates, measurements, events, diagnoses, or other facts that matter to an issue and put them into a clean dataset. From there, you can compare those facts against testimony.
A clear use case, if a witness says symptoms began immediately after an incident, you can extract every relevant reference to those symptoms from the medical record and see when they were first documented.
Pair that with Deposition Summaries to jump directly to the witness's testimony with page-line citations. Or use Instant Case Clarity to connect the facts, testimony, and evidence across the wider case and surface places where the record may not line up.
Example 4: Build the Factual Record Around an Expert
Expert opinions are often spread across reports, medical records, depositions, exhibits, and other case materials.
With Fact Extraction, you can define the facts you want to collect around an expert. For example, opinions given, diagnoses relied on, measurements cited, methodologies used, dates examined, or conclusions reached and bring them together in one structured view.
Then you can go further with Expert Witness Investigation, you can look beyond the current record and compare the expert's position with prior testimony and relevant public information, to flag contradictions and weaknesses.
Fact Extraction is now available on newcase.ai.
About newcase.ai
newcase.ai is an AI litigation intelligence platform that connects facts and insights from depositions, medical records, expert testimony, attorney strategy, and case materials into a single searchable intelligence layer.
Built for insurance litigation and complex cases. Legal teams use newcase.ai to produce court-ready medical chronologies, uncover contradictions, cross-reference testimony, investigate experts, and develop case strategy faster than manual review.
newcase.ai is SOC 2 Type II compliant, with strict tenant isolation, encryption in transit and at rest, and regular third-party penetration testing. AI processing operates under a Business Associate Agreement to support HIPAA-compliant workflows, with zero data retention across AI pipelines. Customer materials are never shared, sold, or used for model training.
Media Contact
Company Name: newcase.ai
Contact Person: Mustafa Awad
Email: Send Email
Country: United States
Website: https://www.newcase.ai/contact?utm_source=PR&utm_medium=social&utm_campaign=fact-extraction
