Within a day of going live at a national care organization, Evidently surfaced a decade-old CT scan. It had been scanned in from an out-of-state emergency department, and it showed a small abdominal aortic aneurysm that nobody had ever followed up on. The patient didn’t remember the scan. The provider never saw the scan until they had access to Evidently. A newly ordered scan showed the aneurysm had grown past the threshold for surgery. The provider acted, changing the course of care and saving a life in the process.
The original scan had been buried in their record the whole time, lying in wait. A needle in a haystack of outside documents.
I spent years as an emergency physician, and I still practice hospice and palliative care. In my experience, the biggest challenge with the chart isn’t what’s in it. It’s how much of it goes unread. And when it goes unread, it shows up twice: in the patient’s care, and in a number every hospital CQO and CFO watches, case mix index. The case mix index is the numerical representation of how complex a patient population is. Quality benchmarks and reimbursement are directly tied to this number.
Accurately capturing CMI comes down to where the patient’s history lives: scattered notes in the EHR, scanned outside records, faxes, Care Everywhere documents. A generation of software was built to document for billing, not to read it, so the most consequential details stay trapped where they’re hardest to reach. Am I going to read all 500+ pages on hour seven of a twelve-hour shift, with a full waiting room? Nope. Doesn’t seem fair to the patients in front of me. So the history goes unread.
Patients can tell you how they feel. But most patients don’t know the ejection fraction from an outside echo, or their kidney disease stage. And they’re not likely to bring up the interpersonal violence again that they disclosed to the social worker last year. That part of the story lives in the record. It shapes the workup, the diagnosis, the care and the note. When that context is missing, a gap forms between the patient in the bed, the patient on paper, and the patient who leaves the hospital. Entire departments and dedicated point solutions exist to close this gap, mostly after the fact. What if that gap never formed in the first place?
What the Admit Note Silent Study Found, and How CMI Followed
A complex patient chart is about twice the length of Project Hail Mary. No clinician has time to read that book twice every 15 minutes. Clinical Data Intelligence exists to fill that gap. Evidently reads the whole chart, finds the complexity that will impact care, surfaces it to the provider, and drafts a note documenting that complexity for them to review and edit.
We measure what that changes with our Admit Note Silent Study. Evidently drafts an admit note for each patient from the full record and sets it beside the note the provider actually wrote. Our clinical team reviews every condition that’s in one and not the other.
In every health system where we’ve run it, the finding holds: quality-impacting conditions that were already in the record but never made it into the note, four to five per admit note on average. It holds up independently. In a peer-reviewed study published in Applied Clinical Informatics, clinicians at University of Iowa Health Care found a median of 4.5, with a 97% accuracy rate.
And case mix follows: we’re seeing CMI impact as high as 0.1, and it holds.
I hear the other side of those numbers every week from clinicians: the old echo that changes a heart failure plan, the kidney trend nobody had pieced together, the reason a patient is on a medication nobody could explain. Most of all, they describe the palpable shift in cognitive burden when you can understand a patient’s story in seconds.
Case Mix Starts at the Bedside
The sequence is the same everywhere I’ve seen it. When clinicians start an admission with the whole story, they make better-informed decisions at the bedside, they write a more accurate note, and the case mix index reflects the patients they actually care for.
Every health system has its own decade-old CT buried somewhere in its charts. The only way to know how many is to look. An Admit Note Silent Study runs in the background on your own admissions for a few weeks and gives your team a clinically adjudicated assessment of what you’re missing.
So trust the patient, always. And read what they can’t tell you.
Kai Romero, MD, is Head of Clinical Success at Evidently and a practicing hospice and palliative care physician.
Becker’s 3rd Annual Fall Chief Pharmacy Officer Summit is the top tier event that the people leading the future of pharmacy convene. This 3-day event is built specifically for Chief Pharmacy Officers and senior pharmacy leaders. The sessions examine the workforce, financial and clinical priorities shaping pharmacy today. Becker’s is where candid discussions flourish and new ideas thrive. Becker's 3rd Annual Fall Chief Pharmacy Officer Summit
