NewMissing Records Detection: flags every visit, provider, and date missing from the file. See how →
Home›Solutions›Violence and Risk Review
VIOLENCE AND SEXUAL RISK RECORD REVIEW

A risk instrument is scored from the file, item by item.

Violence and sexual risk record review services assemble the file a structured risk assessment is scored from: institutional and disciplinary records, treatment history, prior evaluations and the documented offence history, each entry page-cited. Scoring and the risk opinion belong to the evaluator.

Click any row → the source page it cites
Risk record digest · Case #IME-4812 documented
Adams, Timothy · institutional record
342 pp / 2 packets received logged
11 duplicate pages removed free
p.140 — wrong patient quarantined
Pages 342 Documents 27 Cited 100%

The coding manual defines the item. The commitment court weighs the opinion.

We do not build for a case type until we can name the standard that defines a correct output and the person who grades the file against it. In violence and sexual-offence risk assessment, both are already published.

The standard and the referee
The rulebook
  • The forum’s sexually violent predator commitment statute, of the kind upheld in Kansas v. Hendricks, 521 U.S. 346 (1997), or the federal civil commitment provision at 18 U.S.C. §4248
  • The coding manual for the instrument the evaluator uses, including the Static-99R rules on what counts as a charge, a conviction and a category, and the HCR-20 Version 3 item definitions
  • The parole or releasing authority’s own published risk policy and the records it requires
  • The APA Specialty Guidelines for Forensic Psychology on data sources and on the limits of a record-based opinion
The referee
  • The commitment court or the parole board, which orders release, commitment or continued detention
  • The respondent’s retained evaluator, who rescores the same items from the same file and litigates every disagreement
  • The treatment provider receiving the case, reading the history it was sent
A score contested because a charge was coded from a summary rather than the underlying record From 10¢ to as low as 5¢/page here, duplicates free
Risk record digest · Case #IME-4812 cited 100%
Packet342 pp / 2 packets · 11 deduplicatedlogged
Offence history documentsCharging, disposition and underlying reportsindexed
Institutional conductDisciplinary findings, dates, outcomescited
Prior evaluationsInstrument, date, scorer, resultflagged
Digest delivered · cited 100% · no scoring, no risk opinion
How it works

3 steps between the file and the assessment.

01

Send the institutional file

Prison and jail records, disciplinary files, treatment and programme records, prior risk evaluations, charging documents and dispositions, and mental health history, in any format.

02

Get the digest back, page-cited

The documented offence history with each entry traced to the underlying document rather than to a summary, institutional conduct in date order, and every prior evaluation with its instrument and result.

03

The evaluator scores and opines

Coding the instrument and forming the risk opinion are the evaluator’s work under their own licence. The digest is the cited record each item is scored from.

The boundary, in writing

A cited record, not a risk score.

We assemble and cite what the file documents. We do not score Static-99R, HCR-20 or any other instrument, estimate recidivism risk, opine on whether a person meets a commitment standard, or recommend release or detention. Those are the evaluator’s and the court’s.

Scoring disputes in these cases are almost always sourcing disputes. An item coded from a presentence summary rather than the charging document is the first thing the opposing evaluator attacks, so every entry in the digest names the document it came from and opens to that page.

Audit trail · Case #IME-4812 exportable
08:12Packet received · 342 pp / 2 packetssystem
08:3111 pages deduplicatedsystem
08:44p.140 flagged — wrong patientsystem
08:54Risk record digest complete · digest delivered · cited 100%system
09:20Risk record digest reviewed · citations verifiedreviewer
09:26Risk record digest exported · scoring worksheet assembled by the evaluatorreviewer
Every access logged · file deleted 30 days after delivery
Why Medrecords AI

The rules the platform never breaks.

Medrecords AI EVERY LINE CITED
CASE #IME-4812 · ADAMS, T.342 pp
2/14 — ER visit, right knee p.4
4/18 — arthroscopic surgery p.61
p.140 — wrong patient quarantined
Medrecords AI
Read every page · cite every line

HIPAA, under a signed BAA

Every file is handled under our Business Associate Agreement, from the first byte.

Never trains a model

Your records are never used to train any AI model — ours or anyone else's.

Every line cited

If we can't cite it, we don't say it. Every sentence links to its source page.

Deleted after delivery

Files are deleted 30 days after delivery, with a full audit log of every access.

Powered by the platform

7 capabilities behind every risk record digest.

The risk record digest is one deliverable of the same platform that reads, sorts, and cites the whole record.

Medical Records OCR

Institutional files across decades and facilities are read in full, including the handwritten disciplinary and segregation logs.

IN ACTION · 2,600 pp / 7 facilities, read in full

Medical Chronology

Charges, dispositions, custody terms, treatment and disciplinary findings assemble on one timeline.

IN ACTION · first contact → current custody, one timeline

Verifiable AI Citations

Every entry links to the underlying document, so an item scored from it survives a rescoring by the other side.

IN ACTION · digest → cited 100%

Medical Summary Reports

It exports into the evaluator’s scoring worksheet and report structure.

IN ACTION · digest → scoring worksheet

Medical Record Deduplication

Forty charts pulled from multiple practices and EHR migrations carry their share of duplicate visit notes. Each is matched and collapsed to one canonical record, so the prescribing pattern is read once per real encounter.

IN ACTION · 40 charts → duplicate visit notes collapsed to 1 record each

Missing Records Identification

A prescribing pattern read across 40 charts is only as sound as the file behind it. When a chart references a visit, refill, or referral that never made it into the production, the gap is flagged before the pattern goes to the board.

IN ACTION · prescribing pattern cross-checked → gaps flagged before submission

Cross-Exam Simulator (beta)

A board investigator or defense counsel builds a case from the chart abstraction. This beta tool maps the questioning a physician facing that hearing is likely to face on the gaps and pattern in their own record. A rehearsal tool, not legal advice.

IN ACTION · prescribing pattern → likely hearing questions mapped (beta)
FAQ

Risk record review, answered.

No. Coding Static-99R or HCR-20 requires trained judgment and belongs to the evaluator who signs the report. We assemble and cite the record each item is scored from, traced to the underlying document.

Because the coding manuals turn on what the underlying record says, not on what a later summary says it says. An item scored from a presentence report is the easiest thing for the other side to rescore and dispute.

Yes. The record does not change with who ordered the review, and a rescoring expert wants exactly the same thing: every item’s source document, with the page.

No. Medrecords AI does not retrieve records from providers or facilities. You bring the records you already have — review starts in minutes from upload. Retrieval vendors take days; you can keep yours and still cut the review to minutes.

Send one file. We'll tell you what we can read.

No obligation. If the case type is buildable we'll scope it; if it isn't, we'll say so.