Predicting patient enrollment in a telephone-based principal care management service using topic modeling

Annisa Marlin Masbar Rus, Julie S Ivy, Min Chi, Mitchell Plyler, Elaine Wells-Gray and Maria E Mayorga

PLOS Digital Health, 2025, vol. 4, issue 9, 1-22

Abstract: Diabetic Retinopathy (DR) is a complication related to diabetes that can lead to vision impairment. To assist DR patients, a care management company provides a telephone-based principal care management (PCM) service, which includes care coaching and other services to reduce barriers to care for patients with DR. Despite its benefits, enrollment in the program is suboptimal. This study developed predictive models using call transcripts to investigate factors associated with patient enrollment in the PCM service. We analyzed transcripts of calls made during the enrollment process (prior to enrollment) and feature-engineered the call metadata (i.e., transcript length, number of calls, time between calls, customer and agent sentiment). In addition, we extracted topics discussed in the transcripts using Structural Topic Modeling (STM) and converted them into vector representations. Utilizing call metadata alongside topics, we developed three classification models (call metadata, topic-based, and topic+metadata) to predict patient enrollment, with the latter demonstrating superior performance. The topic+metadata classification model outperformed the other two models in distinguishing between patient enrollment and non-enrollment, with AUC values ranging from 0.81 to 0.99 across models using 3 to 15-topics. The findings suggest that proactively offering to schedule an appointment after the program benefits explanation leads to a higher odds of enrollment. When the scheduling portion of the conversation is not considered, agents should cover all parts of the script over multiple calls. Additionally, agents who explain the program and maintain longer intervals between calls have higher odds of patient enrollment, suggesting that there is value in allowing patients adequate time to reflect between calls. These findings offer valuable insights for agents to evaluate their strategies in patient enrollment. As the first point of contact, enrollment agents play a crucial role in determining whether patients can benefit from care coordination and management programs.Author summary: Diabetic retinopathy (DR) is a diabetes-related complication that can lead to blindness. Annual eye exams for diabetic patients are crucial for early detection and risk reduction. A telephone-based principal care management (PCM) service offers coaching and assistance to help patients access care, but enrollment in the program is low. We identify the factors that influence enrollment by analyzing transcripts of the conversations between the patient and the PCM agent. These factors include the transcript length, number of calls, time between calls, customer and agent sentiment, as well as the topics discussed. We automatically identified the topics discussed by analyzing groups of unique words that are most likely to occur together in the transcripts of patient-agent conversations and interpreting them into various topic names, such as “program explanation.” After that, we analyzed these factors and found that simply explaining the service to patients is not sufficient. Calls in which agents explain the service and proactively offer to schedule a coaching call are more likely to lead to enrollment. Furthermore, more time between follow-up calls also leads to better enrollment outcomes. Our study provides valuable insights for agents that provide care management services to evaluate their strategies for patient enrollment.

Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0000992 (text/html)
https://journals.plos.org/digitalhealth/article/fi ... 00992&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pdig00:0000992

DOI: 10.1371/journal.pdig.0000992

Access Statistics for this article

More articles in PLOS Digital Health from Public Library of Science
Bibliographic data for series maintained by digitalhealth ().