Built around the physician’s signature
Lexamed helps medical-legal evaluators organize records, check source citations, and prepare a report draft for their own review and signature.
What changes in your review workflow?
Lexamed brings the chronology, source pages, and report draft into a review workspace. The table shows what the application prepares and what you still check.
| Step | What Lexamed prepares | What you review |
|---|---|---|
| Organize the production | A dated chronology and flags linked to source pages | Check missing events, duplicate records, dates, and unreadable pages. |
| Investigate a finding | Quoted evidence and record-grounded answers with citations | Open the cited page and verify the complete statement and clinical meaning. |
| Prepare the report | Editable drafted history and sections for physician writing | Correct the history, add examination findings and medical opinions, then review the saved draft. |
| Take the draft with you | Downloadable chronology and report drafts in Word | Inspect the exported file and complete your independent review before signing. |
Where does the model stop?
Causation, apportionment, impairment and MMI belong to the evaluator. The workflow reserves these sections for your judgment. Generated history may still misstate a source or quote a prior opinion; review and correct it before signing.
Causation
The evaluator determines whether the injury arose out of and in the course of employment. Review generated history for unsupported conclusions.
Apportionment
What share of disability is industrial is left blank for you, with the prior history surfaced beside it.
Impairment
The evaluator supplies the impairment rating. Check extracted findings and any quoted prior ratings against the source.
Maximal medical improvement
Whether the applicant is permanent and stationary is your determination, not a field the draft fills in.
Can every claim be checked?
Chronology entries are designed to link to source pages and quoted text. The citation checker compares quotations with the extracted page text. A match confirms wording, not clinical meaning or completeness. Missing, unreadable or mismatched sources need review; correct unsupported statements before use.
Review duplicate groups, uncertain dates, and repeated references to earlier studies. Automated grouping can miss duplicates or combine distinct events; confirm that the chronology preserves the original record.
What does it hand back?
Not a timeline to copy from. A draft in the shape the parties expect, with the history assembled and the evaluator’s sections waiting.
- The issues presented, transcribed from each party’s cover letter in the order asked.
- Accounts of how the injury occurred, with source references and differences for you to reconcile.
- Activities of daily living placed in the AMA Guides categories a rating rests on.
- A records-reviewed accounting the draft checks against the record set before you sign the § 4628 declaration.
- The Medical-Legal Fee Schedule service items the review supports, at the published amounts.
How do you know it works?
These tools help evaluate changes. They are not evidence that every release has completed every evaluation. The public scorecard identifies the specific tests, dates and limitations behind the measurements we publish.
A thresholded benchmark
Page counts, classification, duplicate grouping, encounter recall, citation integrity and grounding, each with a pass line a release is reviewed against.
Planted-issue cases
Synthetic fixtures specify the issues expected in a record set. The benchmark then checks whether the pipeline caught each planted issue.
A report judge
The finished draft is checked as a document: that it agrees with itself, with the record set, and with the approved wording for empty sections.
A written launch gate
The evaluation tools support benchmarks, reviewer-decision replay and workflow checks. Available evidence varies by release. A person reads the results and decides whether a model or prompt change ships.
What happens to your work?
This workflow does not fine-tune a model on your uploads. Corrections may be retained for evaluation, replay and synthetic test design. An untouched entry does not count as approval. Review the security and agreement pages for the current data-handling terms; generated outputs still need independent review.
What does it not do yet?
Written here so that nobody has to find out later.
Current access: fictional records only
The public trial accepts fictional records only. Do not upload patient records, including records with names removed.
Real-record access requires approved vendor agreements and hosting, infrastructure and recovery verification, applicable customer terms and business associate agreement acceptance, an accountable readiness review, and explicit enablement for your organization. Accepting an agreement or submitting a request alone does not open access.
Request real-record accessA request starts a conversation about your practice’s needs. It does not authorize patient uploads or commit to a launch date.
- Quality numbers come from planted cases
- The published scorecard describes synthetic tests and their limits. It does not establish clinical accuracy or a completed physician evaluation.
- Real patient records are not accepted yet
- The free trial runs on synthetic records only. The public trial accepts fictional records only. Do not upload patient records, including records with names removed. Real-record access requires approved vendor agreements and hosting, infrastructure and recovery verification, applicable customer terms and business associate agreement acceptance, an accountable readiness review, and explicit enablement for your organization. Accepting an agreement or submitting a request alone does not open access.
- Scale is unproven
- Processing time and completeness depend on the records and scan quality. Large-production performance has not been established by the published evidence; no turnaround guarantee is offered.
- Degraded scans are hard
- Faxed, rotated, low-resolution pages are read with real optical character recognition and flagged when confidence is low. Recovery on the worst pages is partial.
- No practice-system integrations
- Records arrive as PDF uploads. There is no document management or case management connection yet.
Questions physicians ask
- Who is Lexamed for?
- Physicians who write medical-legal reports, such as Qualified Medical Evaluators, Agreed Medical Evaluators and independent medical examiners, and the staff who prepare records for them. The product assembles the history so the physician can spend the review forming opinions.
- Does the AI write any part of the medical-legal opinion?
- The workflow reserves causation, apportionment, impairment and maximal medical improvement for the evaluator. Generated summaries can still contain errors or quote prior opinions; inspect and correct them before use.
- How is a citation checked?
- Each chronology entry carries the page it came from and a verbatim quote. The quote is matched against that page’s text before any model judgement, and an entry whose quote is not on its page stays flagged rather than hidden.
- Is my data used to train the model?
- Lexamed does not fine-tune a model on your uploads through this workflow. Reviewer corrections inform evaluation and synthetic test design. Corrections can also be retained for evaluation and replay of prompts. The audit log records actions separately.
- What does the free trial include?
- The full review workspace on synthetic productions, with nothing to set up and no card at signup. Commercial pricing is published before a paid plan is offered; no automatic conversion.