Code from: Mortality risk estimation for autistic older adults: Comparing novel machine-learning derived weights versus standard weights for the Charlson Comorbidity Index
Data files
Sep 30, 2026 version files 74.39 KB
-
1._Medicare_Cleaning.sas
20.98 KB
-
2._Stochastic_Hill_Climbing.sas
6.85 KB
-
3.__AUC_and_ROC_Plots.sas
6.54 KB
-
4._Table_1_Macro.sas
6.95 KB
-
5._Table_1.sas
3.96 KB
-
Data_Dictionary.docx
25.98 KB
-
README.md
3.11 KB
Abstract
Researchers often use tools like the Charlson Comorbidity Index (CCI) to estimate a person's risk of death. The CCI estimates risk of death based on whether they have 12 health conditions like heart failure, lung disease, dementia, cancer, and others. Each of these health conditions is assigned a ‘weight’ for how much it increases a person’s risk of death, based on data from the general population. But autistic older adults tend to have different patterns of health conditions than the general population. Therefore, the usual CCI may not accurately estimate risk of death for autistic older adults. We created new weights for the 12 health conditions in the CCI using data from autistic older adults. We expected that these new autism-specific weights would predict risk of death within 30-days and 1-year more accurately for autistic older adults.
Dataset DOI: 10.5061/dryad.tdz08kqdh
PROJECT OVERVIEW
This project uses Medicare claims data (Parts A & B) to compare novel machine-learning-derived weights versus standard weights for the Charlson Comorbidity Index predicting mortality risk
Key components:
- Data Cleaning: Prepares raw Medicare claims data for analysis.
- SAS Macros: Creates Table 1.
- Table Generation: Produces descriptive and outcome tables for the cohort.
- Stochastic Hill Climbing: Uses the Stochastic Hill Climbing algorithm to derive weights.
NOTE: This project uses restricted Medicare data that require CMS Data Use Agreement (DUA) approval. The datasets cannot be shared publicly.
TOOLS AND DEPENDENCIES
- Language: SAS v9.4
- Required Access: Secure server with Medicare Parts A & B claims files
- Note: SAS scripts call to "bh" library. This library contains Medicare claims data that must be independently obtained by researchers with authorized access to the Medicare claims data.
- Required SAS Macros: Ensure "4. Table 1 Macro" is saved in the working directory before running table generation and multivariable analyses scripts.
FILE DESCRIPTIONS
1._Medicare_Cleaning.sas
- Cleans and prepares data
2._Stochastic_Hill_Climbing.sas
- Performs machine-learning algorithm
3.__AUC_and_ROC_Plots.sass
- Calculates AUC and prepares for plots
4._Table_1_Macro.sas
- Macro to produce descriptive statistics
5._Table_1.sas
- Generates descriptive statistics for cohort
Data_Dictionary.docx
- Variable names and definitions
- Variables described are those used in the analysis or necessary to create variables for the analysis
READme.txt
- Project overview and instructions
HOW TO RUN
/* Step 1: Data Cleaning */
Run the file "1. Medicare Cleaning.sas"
/* Step 2: Stochastic Hill Climbing */
Run the file "2. Stochastic Hill Climbing.sas"
/* Step 3: Performance */
Run the file "3. AUC and ROC Plots.sas"
/* Step 4: Table 1 */
Run the file "4. Table 1 Macro.sas"
Run the file "5. Table 1.sas"
OUTPUTS
Table 1 MB 24NOC2025.rtf Descriptive statistics
DATA USE DISCLAIMER
Medicare data are protected under CMS Data Use Agreements. This repository does NOT include raw data. Users must obtain appropriate DUA approval to access Medicare claims.
CITATION
The project affiliated with these scripts is the following:
Madison Blake, Melica Nikahd, J Madison Hyer, Brian W Patterson, Bethany J Wolf, Lauren Bishop, and Brittany N Hand Mortality risk estimation for autistic older adults: comparing novel machine-learning derived weights versus standard weights for the Charlson Comorbidity Index. (2026) Journal of Comparative Effectiveness Research. DOI: 10.57264/cer-2026-0053
Human subjects data
Medicare data are protected under CMS Data Use Agreements. This repository does NOT include raw data. Users must obtain appropriate DUA approval to access Medicare claims.