From 56d92625857198dc180db3324a5ea5998af03d8b Mon Sep 17 00:00:00 2001
From: Levi Neuwirth <ln@levineuwirth.org>
Date: Sat, 11 Apr 2026 23:55:57 -0400
Subject: [PATCH] auto: 2026-04-12T03:55:57Z

---
 content/essays/beyond-comorbidity-indices/index.md | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/content/essays/beyond-comorbidity-indices/index.md b/content/essays/beyond-comorbidity-indices/index.md
index 2a22757..64054f2 100644
--- a/content/essays/beyond-comorbidity-indices/index.md
+++ b/content/essays/beyond-comorbidity-indices/index.md
@@ -30,14 +30,18 @@ history:
     note: Preprint auto-formatted for levineuwirth.org
 ---
 
-::: {.annotation .annotation--collapsible}
-**KEY POINTS**
-
+::: {.annotation .annotation--static}
+<div class="annotation-header">
+<span class="annotation-label">Summary</span>
+<span class="annotation-name">Key points</span>
+</div>
+<div class="annotation-body">
 **Question.** Among adult hospitalizations in a national claims database, does a deep learning model using ICD-10-CM diagnosis codes improve prediction of 30-day unplanned readmission and 30-day postdischarge in-hospital mortality compared with benchmark models based on Charlson and Elixhauser comorbidity indices?
 
 **Findings.** In this cohort study of 3,226,831 temporally held-out discharges, the ICD-10-CM--based model showed better discrimination than benchmark comorbidity-index models for both outcomes.
 
 **Meaning.** Using the full set of discharge diagnosis codes may improve short-term claims-based outcome prediction beyond summary comorbidity indices.
+</div>
 :::
 
 ## Introduction (Background and Significance)