<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Reveiqcompany on Medium]]></title>
        <description><![CDATA[Stories by Reveiqcompany on Medium]]></description>
        <link>https://medium.com/@reveiqcompany?source=rss-d2b2fcf94607------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/0*19nUKNS3JerFl_za</url>
            <title>Stories by Reveiqcompany on Medium</title>
            <link>https://medium.com/@reveiqcompany?source=rss-d2b2fcf94607------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sun, 22 Nov 2026 23:44:55 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@reveiqcompany/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[DIPA: An Analytics Sequence, Borrowed for the Clinical Note]]></title>
            <link>https://medium.com/@reveiqcompany/dipa-an-analytics-sequence-borrowed-for-the-clinical-note-c2079bbcd1ce?source=rss-d2b2fcf94607------2</link>
            <guid isPermaLink="false">https://medium.com/p/c2079bbcd1ce</guid>
            <category><![CDATA[healthcare]]></category>
            <category><![CDATA[clinical-documentation]]></category>
            <category><![CDATA[ai-healthcare-solutions]]></category>
            <category><![CDATA[revenue-cycle-management]]></category>
            <category><![CDATA[medical-coding]]></category>
            <dc:creator><![CDATA[Reveiqcompany]]></dc:creator>
            <pubDate>Sat, 19 Sep 2026 19:24:52 GMT</pubDate>
            <atom:updated>2026-09-19T19:24:52.650Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*c6cvw7YP6YNuTrYB992UiQ.png" /></figure><p><strong>Describe. Interpret. Predict. Act.</strong></p><p>Every analytics team in healthcare works through the same four questions in the same order. What is happening? Why is it happening? What is likely to happen next? What should we do about it? Descriptive, diagnostic, predictive, prescriptive. It is the standard maturity model, and it is how a dashboard earns its place.</p><p>DIPA is that sequence applied to the clinical note, because clinicians already reason in exactly this order. The difference is that only the first two steps reliably reach the chart.</p><p>The four elements</p><p>Describe. What is happening with this patient now. Findings, objective data, response to treatment, and change from this patient’s own baseline.</p><p>Interpret. What it means clinically and why it is happening. Diagnosis, etiology, acuity, severity, and how the conditions relate to each other.</p><p>Predict. What the expected course is, and what would tell you it is not going well. Trajectory, deterioration signals, monitoring requirements, and escalation criteria written as observable conditions.</p><p>Act. What the team is doing, monitoring, and escalating. Treatment, reassessment interval, escalation plan, and disposition requirements.</p><p>DIPA does not replace SOAP. It sits on top of it. Describe and Interpret map onto what you already write in Subjective, Objective, and Assessment. The framework adds nothing to those. What it asks for is the third and fourth steps, which most notes leave out because the reasoning happened in your head and never needed to be written down when you were the one coming back in four hours.</p><p>Why this matters more now than it did five years ago</p><p>Ambient AI scribes are very good at Describe. They capture the encounter, organize the findings, and produce a clean, complete, well-structured account of what was said and what was observed. They are competent at Interpret when you say the assessment out loud.</p><p>They are structurally incapable of Predict.</p><p>Prediction is not in the room. It is not in the transcript. Your judgment about where this patient is heading, what would change your mind about the diagnosis, and what threshold would make you escalate exists only in your head unless you say it or type it. A scribe cannot capture reasoning you never externalized.</p><p>So the notes are getting longer and more thorough while the part that carries the most clinical value is quietly disappearing. A beautifully structured AI-generated note that contains no anticipatory reasoning is a more complete record of a less complete thought.</p><p>DIPA gives you a four-word prompt for what to say out loud so that the scribe captures it.</p><p>The foreseeability objection, and why the framework survives it</p><p>The obvious objection comes up in the first five minutes of any physician meeting, and it is a fair one.</p><p>If I document that this patient is at risk for septic shock, and they progress to septic shock, have I not just written the plaintiff’s exhibit? Documented foreseeability plus a bad outcome looks like a gift to opposing counsel.</p><p>The risk is real. It is also specific, and it comes from unpaired prediction, meaning anticipated risk recorded with no corresponding response. That is why DIPA has exactly one mandatory rule:</p><p>A Predict statement without a corresponding Act statement is not DIPA documentation.</p><p>Predict and Act are one move, not two. If you name the risk, you name the monitoring parameter, the reassessment interval, or the escalation criterion that answers it.</p><p>Paired, the record reads very differently. It shows a clinician who recognized a risk, planned for it, and told the team what would trigger a change. That is contemporaneous evidence of sound anticipatory reasoning, and it is what defends care when the outcome is bad despite everything being done correctly. Reasonable clinicians reach wrong conclusions from reasonable reasoning. The defensible version of that is a documented thought process. The indefensible version is a conclusion with no visible reasoning behind it.</p><p>None of this is new clinical behavior. Failure to rescue has been a recognized quality construct for decades, and early warning systems exist precisely because anticipating trajectory changes outcomes. DIPA does not ask you to think differently. It asks you to make visible the thinking you already do.</p><p>Two places it is immediately useful</p><p>DIPA was presented recently at a revenue cycle conference, which is an unusual venue for a documentation framework aimed at clinicians. Two use cases explain why.</p><p>The Risk element of medical decision making</p><p>E and M level selection under the 2023 guidelines rests on problems addressed, data reviewed, and risk of complications or morbidity of patient management. Risk is the element clinicians document worst, and the reason is structural. You document what you did, not what could have happened. The note says “started antibiotics, admitted.” It does not say what the patient was at risk for, why admission rather than outpatient treatment, or what would change that decision.</p><p>That is Predict, in coding language. Writing it down is not upcoding. It is recording the work you actually performed, and it moves levels in both directions honestly. The purpose is a complete record of your reasoning. The coding accuracy is a consequence.</p><p>Present on admission determination for conditions that declare themselves later</p><p>This is the inpatient case that generates the most interest.</p><p>Some conditions are present at admission but not diagnosable at admission. A pressure injury developing under the skin. Sepsis evolving from an infection that has not yet met criteria. Acute kidney injury in the early phase. The patient arrives with the process already underway and it becomes apparent on day two or day three.</p><p>Coding rules generally allow a condition documented as suspected or possible at the time of admission, and later confirmed, to be assigned as present on admission. But that requires the suspicion to be in the admission documentation. If the first mention appears on day three, the record looks like a hospital-acquired condition, with the quality measure and payment consequences that follow.</p><p>A Predict statement written at admission is precisely that documentation. “At risk for evolving sepsis given the source and current trajectory; monitoring lactate, mental status, and hemodynamics” is clinical reasoning first and a POA anchor second. It costs one sentence.</p><p>And here is the part that holds even when the coding rules do not cooperate.</p><p>Language like “evolving” or “at risk for” may not be codable on its own. That varies by setting, by the specific guideline, and by whether the condition is ultimately confirmed. Do not write a Predict statement expecting it to be picked up as a diagnosis, because often it will not be.</p><p>What it does reliably is give your CDI and coding teams something to work with.</p><p>A concurrent CDI reviewer reading your day one note sees the risk you named and can bring you a clarification while the patient is still in front of you and you still remember the case. A coder reaching the account before final billing has a documented basis to ask whether the condition was in fact present on admission, rather than assuming it was not. The query becomes a reasonable clinical question grounded in your own words instead of a request that arrives out of nowhere weeks later.</p><p>Without that sentence there is nothing to ask about. Silence in the admission note is not neutral. It closes the question before anyone can raise it, and the account codes as though the condition began in your hospital.</p><p>This is the same logic that runs through the rest of the framework. Making the reasoning visible while it can still change something beats reconstructing it afterwards. A query answered on day two costs you thirty seconds. The same question after discharge costs a chart review, a retrospective query, a delayed bill, and an answer given from memory.</p><p>Check the specifics against your facility’s coding policy and the current official guidelines, because POA assignment rules are detailed and your coding leadership will have a settled view on them.</p><p>An open framework</p><p>DIPA is published openly by <strong>Matthew Ayinde, MBA, BSN, RN, CCS,</strong> a practicing clinical documentation integrity director. There is no license, no fee, and nothing to buy. Use it, adapt it for your specialty, build it into your templates and smart phrases, and publish what you find, including findings that show no effect.</p><p>The full framework, an ambulatory companion, a pilot charter, and a vendor evaluation guide are available at reveiqai.com/dipa.html.</p><p>A complete note explains what is happening, why it is happening, what may happen next, and what the team is doing about it. The first two are usually there. The framework exists for the other two.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=c2079bbcd1ce" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>