# Onco-Hem Connectome—Network-Based Phenotyping of Polypharmacy and Drug–Drug Interactions in Onco-Hematological Inpatients

## TL;DR

The Onco-Hem Connectome is a network that groups hemato-oncology patients by shared traits, helping identify patterns in drug use and interactions.

## Contribution

A novel patient similarity network for hemato-oncology inpatients that integrates polypharmacy and drug–drug interactions with clinical phenotypes.

## Key findings

- The Onco-Hem Connectome identified five distinct patient communities with varying comorbidity burdens and drug enrichment patterns.
- Communities showed strong alignment between drug signatures, diagnosis patterns, and resource-use variables in hemato-oncology inpatients.
- Robustness analyses confirmed the stability of detected communities using block-equalized features.

## Abstract

We introduce the Onco-Hem Connectome (OHC), a patient similarity network (PSN) designed to organize real-world hemato-oncology inpatients by exploratory phenotypes with potential clinical utility. Background: Polypharmacy and drug–drug interactions (DDIs) are pervasive in hemato-oncology and vary with comorbidity and treatment intensity. Methods: We retrospectively analyzed a 2023 single-center cohort of 298 patients (1158 hospital episodes). Standardized feature vectors combined demographics, comorbidity (Charlson, Elixhauser), comorbidity polypharmacy score (CPS), aggregate DDI severity score (ADSS), diagnoses, and drug exposures. Cosine similarity defined edges (threshold ≥ 0.6) to build an undirected PSN; communities were detected with modularity-based clustering and profiled by drugs, diagnosis codes, and canonical chemotherapy regimens. Results: The OHC comprised 295 nodes and 4179 edges (density 0.096, modularity Q = 0.433), yielding five communities. Communities differed in comorbidity burden (Kruskal–Wallis ε2: Charlson 0.428, Elixhauser 0.650, age 0.125, all FDR-adjusted p < 0.001) but not in utilization (LOS, episodes) after FDR (ε2 ≈ 0.006–0.010). Drug enrichment (e.g., enoxaparin Δ = +0.13 in Community 2; vinblastine Δ = +0.09 in Community 3) and principal diagnoses (e.g., C90.0 23%, C91.1 15%, C83.3 15% in Community 1) supported distinct clinical phenotypes. Robustness analyses showed block-equalized features preserved communities (ARI 0.946; NMI 0.941). Community drug signatures and regimen signals aligned with diagnosis patterns, reflecting the integration of resource-use variables in the feature design. Conclusions: The Onco-Hem Connectome yields interpretable, phenotype-level insights that can inform supportive care bundles, DDI-aware prescribing, and stewardship, and it provides a foundation for phenotype-specific risk models (e.g., prolonged stay, infection, high-DDI episodes) in hemato-oncology.