Background Segmentation techniques are applied in marketing but not fully explored in healthcare. New approaches to patient segmentation might help tailor interventions and communication more specifically to patient needs. The aim of this study was to test a novel peer-to-peer intervention for patients with Type 2 Diabetes (T2D) from within specific patient segments, as identified by using data from primary care EMRs. Approach Patients with T2D from the Eastern Ontario Network (N = 825) were segmented using k-means clustering based on recent medication history. Patients with good and bad control of disease were identified based on A1c, LDL, and BP. Moderated virtual peer-to-peer workshops were held with patients with good and bad control from within and across segments. Patient-reported measures were collected at baseline and after workshops. Results We identified two opposite segments: medication segment (~32%) and lifestyle segment (~15%). The remaining were from intermediate segments. From the first three workshops (medication, lifestyle, and mixed-up groups), we observed that patients in the lifestyle segment were interested in diet, exercise, and identified practical tips. Patients from the medication group were interested in managing the effects of diabetes (stress, sleep) and they did not identify strategies for managing their disease. Conclusions Patients from lifestyle segment reported better learning experience and higher motivation to set a goal, suggesting that the proposed approach might be appropriate for this subgroup of patients. Future research is needed to investigate possible approaches tailored to the needs of patients from the medication segment.

Applying Patient Segmentation in Primary Care to Develop Peer-to-Peer Support Groups for Patients with Type 2 Diabetes

Paglialonga A;
2021

Abstract

Background Segmentation techniques are applied in marketing but not fully explored in healthcare. New approaches to patient segmentation might help tailor interventions and communication more specifically to patient needs. The aim of this study was to test a novel peer-to-peer intervention for patients with Type 2 Diabetes (T2D) from within specific patient segments, as identified by using data from primary care EMRs. Approach Patients with T2D from the Eastern Ontario Network (N = 825) were segmented using k-means clustering based on recent medication history. Patients with good and bad control of disease were identified based on A1c, LDL, and BP. Moderated virtual peer-to-peer workshops were held with patients with good and bad control from within and across segments. Patient-reported measures were collected at baseline and after workshops. Results We identified two opposite segments: medication segment (~32%) and lifestyle segment (~15%). The remaining were from intermediate segments. From the first three workshops (medication, lifestyle, and mixed-up groups), we observed that patients in the lifestyle segment were interested in diet, exercise, and identified practical tips. Patients from the medication group were interested in managing the effects of diabetes (stress, sleep) and they did not identify strategies for managing their disease. Conclusions Patients from lifestyle segment reported better learning experience and higher motivation to set a goal, suggesting that the proposed approach might be appropriate for this subgroup of patients. Future research is needed to investigate possible approaches tailored to the needs of patients from the medication segment.
2021
Istituto di Elettronica e di Ingegneria dell'Informazione e delle Telecomunicazioni - IEIIT
diabetes
type 2 diabetes
clustering
patient segmentation
peer-to-peer intervention
collective intelligence
positive deviance
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14243/438885
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact