Text Messaging and Home Blood Pressure Monitoring for Patients with Uncontrolled Hypertension: Proposal for a Feasibility Pilot Randomized Controlled Trial

Patient and Provider Perspectives About the Use of Patient-Generated Health Data During Pregnancy: Qualitative Exploratory Study

BACKGROUND

There is increasing interest in using patient-generated health data (PGHD) to improve patient-centered care during pregnancy. However, little research has examined the perspectives of patients and providers as they report, collect, and use PGHD to inform obstetric care.

OBJECTIVE

This study aims to explore the perspectives of patients and providers about the use of PGHD during pregnancy, including the benefits and challenges of reporting, collecting, and using these data, as well as considerations for expanding the use of PGHD to improve obstetric care.

METHODS

We conducted one-on-one interviews with 30 pregnant or postpartum patients and 14 health care providers from 2 obstetrics clinics associated with an academic medical center. Semistructured interview guides included questions for patients about their experience and preferences for sharing PGHD and questions for providers about current processes for collecting PGHD, opportunities to improve or expand the collection of PGHD, and challenges faced when collecting and using this information. Interviews were conducted by phone or videoconference and were audio recorded, transcribed verbatim, and deidentified. Interview transcripts were analyzed deductively and inductively to characterize and explore themes in the data.

RESULTS

Patients and providers described how PGHD, including physiologic measurements and experience of symptoms, were currently collected during and between in-person clinic visits for obstetric care. Both patients and providers reported positive perceptions about the collection and use of PGHD during pregnancy. Reported benefits of collecting PGHD included the potential to use data to directly inform patient care (eg, identify issues and adjust medication) and to encourage ongoing patient involvement in their care (eg, increase patient attention to their health). Patients and providers had suggestions for expanding the collection and use of PGHD during pregnancy, and providers also shared considerations about strategies that could be used to expand PGHD collection and use. These strategies included considering the roles of both patients and providers in reporting and interpreting PGHD. Providers also noted the need to consider the unintended consequences of using PGHD that should be anticipated and addressed.

CONCLUSIONS

Acknowledging the challenges, suggestions, and considerations voiced by patients and providers can inform the development and implementation of strategies to effectively collect and use PGHD to support patient-centered care during pregnancy.

Identifying Medication-related Intents from a Bidirectional Text Messaging Platform for Hypertension Management: A Pilot Study using a Unsupervised Learning Approach (Preprint)

Background

Free-text communication between patients and providers plays an increasing role in chronic disease management, through platforms varying from traditional health care portals to novel mobile messaging apps. These text data are rich resources for clinical purposes, but their sheer volume render them difficult to manage. Even automated approaches, such as natural language processing, require labor-intensive manual classification for developing training data sets. Automated approaches to organizing free-text data are necessary to facilitate use of free-text communication for clinical care.

Objective

The aim of this study was to apply unsupervised learning approaches to (1) understand the types of topics discussed and (2) learn medication-related intents from messages sent between patients and providers through a bidirectional text messaging system for managing participant blood pressure (BP).

Methods

This study was a secondary analysis of deidentified messages from a remote, mobile, text-based employee hypertension management program at an academic institution. We trained a latent Dirichlet allocation (LDA) model for each message type (ie, inbound patient messages and outbound provider messages) and identified the distribution of major topics and significant topics (probability >.20) across message types. Next, we annotated all medication-related messages with a single medication intent. Then, we trained a second medication-specific LDA (medLDA) model to assess how well the unsupervised method could identify more fine-grained medication intents. We encoded each medication message with n-grams (n=1-3 words) using spaCy, clinical named entities using Stanza, and medication categories using MedEx; we then applied chi-square feature selection to learn the most informative features associated with each medication intent.

Results

In total, 253 participants and 5 providers engaged in the program, generating 12,131 total messages: 46.90% (n=5689) patient messages and 53.10% (n=6442) provider messages. Most patient messages corresponded to BP reporting, BP encouragement, and appointment scheduling; most provider messages corresponded to BP reporting, medication adherence, and confirmatory statements. Most patient and provider messages contained 1 topic and few contained more than 3 topics identified using LDA. In total, 534 medication messages were annotated with a single medication intent. Of these, 282 (52.8%) were patient medication messages: most referred to the medication request intent (n=134, 47.5%). Most of the 252 (47.2%) provider medication messages referred to the medication question intent (n=173, 68.7%). Although the medLDA model could identify a majority intent within each topic, it could not distinguish medication intents with low prevalence within patient or provider messages. Richer feature engineering identified informative lexical-semantic patterns associated with each medication intent class.

Conclusions

LDA can be an effective method for generating subgroups of messages with similar term usage and facilitating the review of topics to inform annotations. However, few training cases and shared vocabulary between intents precludes the use of LDA for fully automated, deep, medication intent classification.

International Registered Report Identifier (IRRID)

RR2-10.1101/2021.12.23.21268061