Patient clusters based on demographics, clinical characteristics, and cancer-related symptoms: a cross-sectional pilot study

Purpose: This study aimed to identify and preliminary validate distinct clusters of patients with13 cancer based on demographics, clinical characteristics, and symptoms and to inform future research14 on sample size requirements for achieving sufficient power in clustering analyses.15 Methods: This cross-sectional pilot study involved 114 patients with cancer from two hospitals in16 northern Italy. Data were collected on demographics, clinical characteristics, and 20 symptoms17 using the Edmonton Symptom Assessment System in October 2022. t-distributed stochastic18 neighbor embedding (t-SNE) was used to reduce the symptom data and demographics (e.g., age)19 into two components, which were then clustered using Ward’s method. A Monte Carlo simulation20 was conducted based on the t-SNE components to estimate the sample size needed to achieve 80! power for different cluster solutions (k = 2, 3, 4).22 Results: Two distinct clusters were identified: Cluster 1 (Higher Symptom Burden Cluster) and23 Cluster 2 (Lower Symptom Burden Cluster). Cluster 1 patients had a higher prevalence of24 depression, anxiety, and drowsiness. Monte Carlo simulations indicated that 50 patients per cluster25 were sufficient for k = 2 clusters to achieve 80% power, whereas 90 patients per cluster were26 needed for k = 3 clusters and 120 patients per cluster for k = 4 clusters.27 Conclusion: This study identified distinct patient clusters and provided preliminary evidence on the28 sample size required for clustering analyses in cancer research. Understanding patient clusters29 enables nurses to provide tailored interventions, potentially improving symptom management and30 overall patient care.