Order from Lab 7D362D

Clinical notes

De-identified clinical encounters from real patients: every note of the stay in full, the final billed codes (ICD-10-CM/PCS, CPT/HCPCS, MS-DRG) with who assigned them, and the claim and clinical outcomes, linked by stable generated patient and encounter ids. It must come with a HIPAA de-identification report, the seller's written authority to license, and commercial training rights that are perpetual for trained weights.

How answering works

Any number of people fill one order. The lab receives one dataset, in its own columns.

Your agent reads the order
It looks at what you hold and says which columns you can fill, and what is missing.
Mora checks what you send
Every record: no copies, no personal data, not already public, not on Mora from someone else.
The lab pays per record it accepts
The lab named the price. You fill as much of the order as you can.

The columns the lab wants

You do not need every column. Mora says which ones each dataset fills.

Column Type What it must hold

encounter_id, patient_id, site_id id Generated ids, stable across records, so notes, codes and outcomes link up and train/test can be split by patient

care_setting, specialty, age_band, sex, payer_class label Inpatient, emergency or outpatient; specialty; who paid

note_type, author_role, written_at label H&P, progress, operative, consult, discharge summary; who wrote it; shifted date

text text The full note, not truncated (often 10,000 to 20,000 characters)

code_system, code_version, code, sequence, present_on_admission, modifier label Final billed ICD-10-CM, ICD-10-PCS, CPT/HCPCS and MS-DRG codes, in order, with the code set year

coded_by_role, coder_credential, coding_method, final_billed label Who assigned the code (CCS, CPC, RHIA), whether by a person or software-suggested and confirmed, and whether it is the code actually billed

claim_status, billed_drg, paid_drg, denial_reason_code, adjudicated_at label Paid, denied or downcoded by the payer, with the reason

discharge_disposition, length_of_stay_days, readmitted_30d, readmission_encounte label Clinical outcome of the stay

deid_method, determination_date, expert_report, date_shift text HIPAA Safe Harbor or Expert Determination, the report, and how dates were shifted

Column	Type	What it must hold
`encounter_id, patient_id, site_id`	id	Generated ids, stable across records, so notes, codes and outcomes link up and train/test can be split by patient
`care_setting, specialty, age_band, sex, payer_class`	label	Inpatient, emergency or outpatient; specialty; who paid
`note_type, author_role, written_at`	label	H&P, progress, operative, consult, discharge summary; who wrote it; shifted date
`text`	text	The full note, not truncated (often 10,000 to 20,000 characters)
`code_system, code_version, code, sequence, present_on_admission, modifier`	label	Final billed ICD-10-CM, ICD-10-PCS, CPT/HCPCS and MS-DRG codes, in order, with the code set year
`coded_by_role, coder_credential, coding_method, final_billed`	label	Who assigned the code (CCS, CPC, RHIA), whether by a person or software-suggested and confirmed, and whether it is the code actually billed
`claim_status, billed_drg, paid_drg, denial_reason_code, adjudicated_at`	label	Paid, denied or downcoded by the payer, with the reason
`discharge_disposition, length_of_stay_days, readmitted_30d, readmission_encounte`	label	Clinical outcome of the stay
`deid_method, determination_date, expert_report, date_shift`	text	HIPAA Safe Harbor or Expert Determination, the report, and how dates were shifted

How much, in the lab's words

2 million coded encounters (about 10 million notes) from 20 or more sites, 2019 to 2025. A first buy of 200,000 encounters is useful.

encounters
notes
codes
coding-audit
claim-outcome
clinical-outcome
deidentification