# Home Health OASIS Documentation Review > Every OASIS item checked against the documentation behind it, with the clinical grouping and payment component identified and each item page-cited. Canonical page: https://medrecords.ai/solutions/oasis-documentation-review/ --- [Home](https://medrecords.ai/) ›[Solutions](https://medrecords.ai/solutions/) ›OASIS Documentation Review HOME HEALTH OASIS DOCUMENTATION REVIEW ## The assessment drives the payment. The visit note has to back it. OASIS documentation review services check each coded item against the visit documentation supporting it, and identify which PDGM component the item drives. Unsupported items are flagged with their grouping impact, and the correction and submission decisions stay with your clinical manager. [Test a file ](https://medrecords.ai/test-a-file/?src=oasis-documentation-review) [Book a demo](https://medrecords.ai/demo/) Click any row → the source page it cites Item review · Case #IME-4812 documented Adams, Timothy · OASIS assessment and visit notes 342 pp / 2 packets received logged 11 duplicate pages removed free p.140 — wrong patient quarantined Pages 342 Documents 27 Cited 100% ### The guidance manual is published. So is the reviewer who applies it. 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 OASIS review, both are already published. The standard and the referee The rulebook - The CMS OASIS Guidance Manual, which defines each item, its time point, and its response-specific instructions - The PDGM grouping logic, which maps the primary diagnosis, functional impairment level and comorbidity adjustment to a payment group - 42 CFR §484.55, which requires a comprehensive assessment of each patient - The agency's own clinical documentation policy, where it goes beyond the manual The referee - The MAC and the UPIC, on additional documentation requests and targeted probe and educate - The HHS Office of Inspector General, whose home health audits target unsupported functional scoring - The state survey agency, where an inaccurate comprehensive assessment is a condition-level concern Repayment on an audited episode, and the review cycle that follows it Flat 10¢/page here, duplicates free Item review · Case #IME-4812 cited 100% Packet342 pp / 2 packets · 11 deduplicatedlogged Coded itemsChecked against the visit notescited Functional scoringDocumentation across the assessmentcited Unsupported itemsCoded with nothing behind itflagged Review delivered · cited 100% · no OASIS coded or transmitted How it works ### 3 steps between the assessment and the claim. 01 #### Send the OASIS and the notes The completed assessment plus the visit documentation behind it, including the clinician's narrative, in any format. 02 #### We return the review, page-cited Each coded item matched to the documentation supporting it, unsupported items flagged, and the PDGM component each one drives identified. 03 #### Your clinical manager decides Correction, clinician follow-up and transmission stay with your agency. We never code an item or transmit an assessment. The boundary, in writing ### A check against the notes, not a coded assessment. We compare the coded items to the visit documentation and cite what supports them. We do not code OASIS, correct an assessment, transmit to CMS, or determine a payment amount. Those are your clinical manager's and your agency's responsibilities under the guidance manual. The review runs in both directions. Items the documentation supports more strongly than they were coded are flagged too, because a one-directional review is a revenue exercise rather than a control. Audit trail · Case #IME-4812 exportable 08:12Packet received · 342 pp / 2 packetssystem 08:3111 pages deduplicatedsystem 08:44p.140 flagged — wrong patientsystem 08:54Item review complete · review complete · items checked · cited 100%system 09:20Item review reviewed · citations verifiedreviewer 09:26Item review exported · correction decision made off-platformreviewer Every access logged · file deleted 30 days after delivery Why Medrecords AI ### The rules the platform never breaks. 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 ### 4 capabilities behind every item review. The item review is 1 deliverable of the same platform that reads, sorts, and cites the whole record. [ #### Medical Records OCR Every page read in full — visit notes, clinician narratives, wound photos, handwritten flowsheets — nothing skipped, nothing guessed. IN ACTION · 342 pp / 2 packets → 27 documents, read in full ](https://medrecords.ai/product/ocr/) [ #### Medical Chronology The episode builds itself into a timeline, so functional status can be read across visits rather than at a single point. IN ACTION · start of care → recertification, 1 continuous timeline ](https://medrecords.ai/product/chronology/) [ #### Verifiable AI Citations If we can't cite it, we don't say it. Every reviewed item links to the visit note page behind it. IN ACTION · every item → cited 100% ](https://medrecords.ai/product/citations/) [ #### Medical Summary Reports The review formats straight into the compliance file — your template, your letterhead. IN ACTION · item review → correction worklist ](https://medrecords.ai/product/summaries/) FAQ ### OASIS documentation review, answered. No. We check coded items against the visit documentation and cite it. Coding, correcting an assessment, and transmitting it stay with your clinical manager and your agency, under the CMS guidance manual. It identifies which PDGM component each flagged item drives, so the significance of a correction is visible. Calculating the episode payment and deciding what to do about a claim stays with your agency. No. Items the documentation supports more strongly than they were coded are flagged as well. A review that only moves one way is a revenue exercise, and a UPIC reviewer will read it as one. 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 1 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. [Test a file ](https://medrecords.ai/test-a-file/?src=oasis-documentation-review) [Book a demo](https://medrecords.ai/demo/) [See every case type we process →](https://medrecords.ai/solutions/case-types/)