Exploratory Research in Clinical and Social Pharmacy - Using network analysis modularity to group health code systems and decrease dimensionality in machine learning models

Aug 2, 2026

Uploaded by Noah

Machine learning prediction models in healthcare and clinical pharmacy research face difficulties when encoding high-dimensional Healthcare Coding Systems (HCSs) such as ICD, ATC, and DRG, because dimensionality reduction can cause information loss. The study investigates Network Analysis modularity as a way to group HCSs to improve encoding for ML tasks. Using MIMIC-III, ICD-9 codes form nodes and patient co-occurrence edges, modularity detection generates modules, and grouping strategies are evaluated for predicting 90-day ICU readmissions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Abstract

Background and objectives

Methods and evaluation approach

Results and conclusions

Introduction

Exploratory Research in Clinical and Social Pharmacy 14 (2024) 100463 Contents lists available at ScienceDirect Exploratory Research in Clinical and Social Pharmacy journal [homepage: www.elsevier.com/locate/rcsop](homepage: www.elsevier.com/locate/rcsop) | “Using network analysis modularity to group health code systems and decrease dimensionality in machine learning models” | | | | | --- | --- | --- | --- | | Mohsen Askara, *, Lars Småbrekke a, Einar Holsbøb, Lars Ailo Bongob, Kristian Svendsen a
a Department of Pharmacy, Faculty of Health Sciences, UiT-The Arctic University of Norway, PO Box 6050, Stakkevollan, N-9037 Tromsø, Norway
b Department of Computer Science, Faculty of Science and Technology, UiT-The Arctic University of Norway, PO, Box 6050 Stakkevollan, N-9037 Tromsø, Norway | | | | | A R T I C L E I N F O | | A B S T R A C T | | | Keywords:
Predictive modeling Machine learning Network analysis Modularity detection Healthcare coding systems Categorical data encoding | | Background: Machine learning (ML) prediction models in healthcare and pharmacy-related research face challenges with encoding high-dimensional Healthcare Coding Systems (HCSs) such as ICD, ATC, and DRG codes, given the trade-off between reducing model dimensionality and minimizing information loss.
Objectives: To investigate using Network Analysis modularity as a method to group HCSs to improve encoding in ML models.
Methods: The MIMIC-III dataset was utilized to create a multimorbidity network in which ICD-9 codes are the nodes and the edges are the number of patients sharing the same ICD-9 code pairs. A modularity detection algorithm was applied using different resolution thresholds to generate 6 sets of modules. The impact of four grouping strategies on the performance of predicting 90-day Intensive Care Unit readmissions was assessed. The grouping strategies compared: 1) binary encoding of codes, 2) encoding codes grouped by network modules, 3) grouping codes to the highest level of ICD-9 hierarchy, and 4) grouping using the single-level Clinical Classification Software (CCS). The same methodology was also applied to encode DRG codes but limiting the comparison to a single modularity threshold to binary encoding.
The performance was assessed using Logistic Regression, Support Vector Machine with a non-linear kernel, and Gradient Boosting Machines algorithms. Accuracy, Precision, Recall, AUC, and F1-score with 95% confidence intervals were reported.
Results: Models utilized modularity encoding outperformed ungrouped codes binary encoding models. The accuracy improved across all algorithms ranging from 0.736 to 0.78 for the modularity encoding, to 0.727 to 0.779 for binary encoding. AUC, recall, and precision also improved across almost all algorithms. In comparison with other grouping approaches, modularity encoding generally showed slightly higher performance in AUC, ranging from 0.813 to 0.837, and precision, ranging from 0.752 to 0.782.
Conclusions: Modularity encoding enhances the performance of ML models in pharmacy research by effectively reducing dimensionality and retaining necessary information. Across the three algorithms used, models utilizing modularity encoding showed superior or comparable performance to other encoding approaches. Modularity encoding introduces other advantages such as it can be used for both hierarchical and non-hierarchical HCSs, the approach is clinically relevant, and can enhance ML models’ clinical interpretation. A Python package has been developed to facilitate the use of the approach for future research. | | Abbreviations: ATC, Anatomical Therapeutic Chemical classification; AUC, Area Under the Curve; CCS, Clinical Classification Software; CPT, Current Procedural Terminology; DRG, Diagnosis Related Groups; ED, Emergency Department; EDA, Exploratory Data Analysis; GBM, Gradient Boosting Machine; HCPCS, Healthcare Common Procedure Coding System; HCSs, Healthcare Codin

FAQs

Why is encoding Healthcare Coding Systems (HCSs) challenging for machine learning models?

High-dimensional HCS features (e.g., ICD, ATC, DRG) must be encoded for ML, but reducing dimensionality risks losing important information.

How does the study use network analysis modularity to group health code systems?

ICD-9 codes are modeled as nodes with edges weighted by the number of patients sharing code pairs, then modularity detection with multiple resolution thresholds produces module sets used for grouped encoding.

What were the main findings for 90-day ICU readmission prediction?

Models using modularity encoding outperformed ungrouped binary encoding across algorithms, with improvements in accuracy and generally higher AUC, recall, and precision compared with other grouping approaches.

Aug 2, 2026

Uploaded by Noah