<?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 Arunahebatam on Medium]]></title>
        <description><![CDATA[Stories by Arunahebatam on Medium]]></description>
        <link>https://medium.com/@arunahebatam?source=rss-d780fa97b2b8------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/0*4Xokkd-7fUsTVybV</url>
            <title>Stories by Arunahebatam on Medium</title>
            <link>https://medium.com/@arunahebatam?source=rss-d780fa97b2b8------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Thu, 19 Nov 2026 22:23:52 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@arunahebatam/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[Visualizing Systemic Inflammatory Response Syndrome (SIRS) in ICU Patients]]></title>
            <link>https://medium.com/@arunahebatam/visualizing-systemic-inflammatory-response-syndrome-sirs-in-icu-patients-d2561cb8b4b2?source=rss-d780fa97b2b8------2</link>
            <guid isPermaLink="false">https://medium.com/p/d2561cb8b4b2</guid>
            <category><![CDATA[tableau]]></category>
            <category><![CDATA[sir]]></category>
            <category><![CDATA[sql]]></category>
            <dc:creator><![CDATA[Arunahebatam]]></dc:creator>
            <pubDate>Tue, 17 Nov 2026 21:02:59 GMT</pubDate>
            <atom:updated>2026-11-17T21:02:59.617Z</atom:updated>
            <content:encoded><![CDATA[<p>What is SIRS?</p><p>Systemic Inflammatory Response Syndrome (SIRS) is an exaggerated defense response of the body to a harmful stressor such as infection, trauma, surgery, acute inflammation, or ischemia. Clinically, SIRS is identified when a patient meets <strong>two or more</strong> of four specific physiological criteria: abnormal body temperature, elevated heart rate (tachycardia), rapid breathing (tachypnea), or an abnormal white blood cell (WBC) count. In the ICU, detecting SIRS early is critical because it serves as the earliest clinical warning sign of potential sepsis and multi-organ dysfunction.</p><p>The Problem with Raw ICU Data</p><p>The dataset used for this analysis contains <strong>44 clinical fields and over 1.55 million hourly rows</strong> across 40,336 ICU patients. Because vital signs and lab results are recorded continuously at different intervals, raw ICU data is high in volume, noisy, and complex. Clinicians track parameters such as Temperature, Heart Rate, Respiratory Rate, and White Blood Cell (WBC) count. Without structured aggregation, spotting the exact hour a patient transitions from stable vitals to an active SIRS trigger is nearly impossible.</p><p>Raw Data to Clinical Insights Using the SIRS Score</p><p>To turn scattered hourly vitals into an actionable clinical indicator, I built a composite <strong>SIRS Score</strong> in Tableau. By evaluating each vital sign against standard clinical thresholds and combining them into a single hourly score (0 to 4), clinicians can immediately separate normal physiological fluctuations from true inflammatory warning signs — and pinpoint the exact hour a patient crosses the critical threshold (SIRS Score &gt;= 2).</p><p>Visualizing SIRS in Tableau</p><p>Using Tableau, raw patient logs are transformed into an interactive early-warning dashboard that identifies <strong>which patients</strong> are triggering SIRS, <strong>which age groups</strong> are most vulnerable, and <strong>how fast</strong> it happens after admission.</p><p><strong>1. SIRS Score &amp; Patient Screening (Donut Chart)</strong></p><p>To separate high-risk inflammatory cases from stable admissions across the ICU population, individual vital sign flags are evaluated using conditional logic and Level of Detail (LOD) expressions, then visualized as a <strong>Donut Chart</strong> to show the overall proportion of affected patients.</p><p><strong>Calculated Fields Used:</strong></p><ol><li><strong>SIRS Score</strong></li></ol><p>tableau</p><pre>(IF [Temp] &gt; 38 OR [Temp] &lt; 36 THEN 1 ELSE 0 END) +<br>(IF [HR] &gt; 90 THEN 1 ELSE 0 END) +<br>(IF [Resp] &gt; 20 OR [PaCO2] &lt; 32 THEN 1 ELSE 0 END) +<br>(IF [WBC] &gt; 12 OR [WBC] &lt; 4 THEN 1 ELSE 0 END)</pre><ol><li><strong>Observed SIRS Status</strong></li></ol><p>tableau</p><pre>IF { FIXED [Patient ID] : MAX([SIRS Score]) } &gt;= 2 THEN &quot; SIRS&quot;<br>ELSE &quot;No SIRS&quot;<br>END</pre><ol><li><strong>Percentage of Total Patients</strong></li></ol><p>tableau</p><pre>COUNTD([Patient ID]) / TOTAL(COUNTD([Patient ID]))</pre><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*E0UkW2ZSwsoEHhhPr5yT7g.png" /></figure><p><strong>How it works:</strong> The <strong>SIRS Score</strong> formula checks all four clinical vital signs every hour and assigns 1 point for each abnormal reading. Next, { FIXED [Patient ID] : MAX([SIRS Score]) } evaluates every patient across their entire ICU stay to see if they ever reached the clinical SIRS threshold (&gt;= 2). Visualizing this split in a <strong>Donut Chart</strong> makes the scale of risk immediately clear: out of 40,336 total ICU patients, <strong>26,508 patients (65.7%)</strong>triggered initial SIRS warning signs, while <strong>13,828 patients (34.3%)</strong> remained in the Non-Observed SIRS group.</p><p><strong>2. SIRS Distribution by Age Category</strong></p><p>Once high-risk patients are identified, segmenting them by age helps clinicians spot demographic vulnerability across Observed and Non-Observed SIRS groups.</p><p><strong>Calculated Field Used:</strong></p><ol><li><strong>Age Category</strong></li></ol><p>tableau</p><pre>IF [Age] &lt;= 18 THEN &quot;0-18&quot;<br>ELSEIF [Age] &lt;= 39 THEN &quot;20-39&quot;<br>ELSEIF [Age] &lt;= 59 THEN &quot;40-59&quot;<br>ELSEIF [Age] &lt;= 79 THEN &quot;60-79&quot;<br>ELSE &quot;80+&quot;<br>END</pre><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*e9wC0FPAkCrw0g6ttn8bDQ.png" /></figure><p><strong>How it works:</strong> Grouping continuous patient ages into five clean clinical brackets reveals clear demographic patterns. Visualizing this breakdown in a Trellis chart highlights that <strong>patients in the 60–79 age category represent the highest volume</strong> in both Observed and Non-Observed SIRS cohorts. Segmenting patients by age helps ICU teams anticipate which age groups require more frequent vital sign checks and earlier diagnostic screening.</p><p><strong>3. Trigger Hour Distribution by Bin</strong></p><p>After identifying <em>who</em> triggers SIRS and <em>which age groups</em> are most affected, the final step is measuring <strong>how quickly</strong> after ICU admission patients cross the SIRS Score &gt;= 2 threshold.</p><p><strong>Calculated Fields Used:</strong></p><ol><li><strong>Trigger Hour</strong></li></ol><p>tableau</p><pre>{ FIXED [Patient ID] : MIN(IF [SIRS Score] &gt;= 2 THEN [ICULOS] END) }</pre><ol><li><strong>Trigger Hour Bin</strong></li></ol><p>tableau</p><pre>IF [Trigger Hour] &lt;= 10 THEN &quot;0-10 hrs&quot;<br>ELSEIF [Trigger Hour] &lt;= 20 THEN &quot;11-20 hrs&quot;<br>ELSEIF [Trigger Hour] &lt;= 30 THEN &quot;21-30 hrs&quot;<br>ELSEIF [Trigger Hour] &lt;= 40 THEN &quot;31-40 hrs&quot;<br>ELSEIF [Trigger Hour] &lt;= 50 THEN &quot;41-50 hrs&quot;<br>ELSE &quot;&gt;50 hrs&quot;<br>END</pre><ol><li><strong>Percentage of Patients</strong></li></ol><p>tableau</p><pre>COUNTD([Patient ID]) / TOTAL(COUNTD([Patient ID]))</pre><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*xayMI26upIaBdvLzIFYQXA.png" /></figure><p><strong>How it works:</strong> Because a single patient can have dozens of hourly records where their SIRS score fluctuates, { FIXED [Patient ID] : MIN(...) } scans each patient&#39;s timeline and isolates the <strong>very first hour</strong> they cross SIRS Score &gt;= 2. Grouping those trigger hours into 10-hour intervals and dividing distinct patients by the total reveals a critical clinical insight: <strong>69% of initial SIRS triggers occur within the first 10 hours of ICU admission.</strong></p><p>How Visualization Improves Clinical Outcomes</p><p>A well-structured SIRS dashboard shifts ICU care from reactive to proactive. Instead of manually scanning spreadsheets of hourly lab values, clinicians can immediately see which patients have crossed the SIRS &gt;= 2threshold, which age groups carry the highest risk, and how many hours have elapsed since admission. Early visibility leads to faster fluid resuscitation, timely blood cultures, and earlier intervention before SIRS progresses into severe sepsis or multi-organ failure.</p><p>Conclusion</p><p>In the analysis of ICU patients, visualizing SIRS triggers revealed that <strong>65.7% of ICU patients trigger SIRS</strong>and <strong>nearly 7 out of 10 of those events happen within the first 10 hours of admission</strong>, with older adults (ages 60–79) carrying the highest burden. SIRS is the body’s earliest alarm bell. When raw hourly ICU data is structured through Tableau calculated fields and transformed into visual intelligence, clinicians gain the time they need to intervene early and save lives.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=d2561cb8b4b2" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>