Generalizing from qualitative data: a case example using critical realist thematic analysis and mechanism mapping to evaluate a community health worker-led screening program in India

Abstract

Background: A central goal of implementation science is to generate insights that allow evidence-based practices to be successfully applied across diverse settings. However, challenges often arise in preserving programs' effectiveness outside the context of their intervention development. We propose that qualitative data can inform generalizability via elucidating mechanisms of an intervention. Critical realist thematic analysis provides a framework for applying qualitative data to identify causal relationships. This approach can be used to develop mechanism maps, a tool rooted in policy that has been used in health systems interventions, to explain how and why interventions work. We illustrate use of these approaches through a case example of a community health worker (CHW)-delivered gestational diabetes (GDM) screening intervention in Pune, India. CHWs successfully improved uptake of oral glucose tolerance tests (OGTT) among pregnant women, however clinical management of GDM was suboptimal.

Methods: Qualitative interviews were conducted with 53 purposively sampled participants (pregnant women, CHWs, maternal health clinicians). Interview transcripts were reviewed using a critical realist thematic analysis approach to develop a coding scheme pertinent to our research questions: "What caused high uptake of GDM screening?" and "Why did most women with GDM referred to clinics did not receive evidence-based management?". Mechanism maps were retrospectively generated using short- and long-term outcomes as fenceposts to illustrate causal pathways of the CHW-delivered program and subsequent clinical GDM management.

Results: Critical realist thematic analysis generated mechanism maps showed that CHWs facilitated GDM screening uptake through affective, cognitive and logistic pathways of influence. Lack of evidence-based treatment of GDM at clinics was caused by 1) clinicians lacking time or initiative to provide GDM counseling and 2) low perceived pre-test probability of GDM in this population of women without traditional risk factors. Mechanism mapping identified areas for adaptation to improve the intervention for future iterations.

Conclusions: Mechanism maps created by repeated engagement following the critical realist thematic analysis method can provide a retrospective framework to understand causal relationships between factors driving intervention successes or failures. This process, in turn, can inform the generalizability of health programs by identifying constituent factors and their interrelationships that are central to implementation.

Keywords: Critical realism; Generalizing; Mechanism mapping; Qualitative data.

Fig. 1

Logic model summarizing the proposed theory of change of CHW-facilitated GDM screening

Fig. 2

Anticipated short- and medium-term outcomes serve as fenceposts for the intervention’s mechanism map

Fig. 3

Mechanism map explaining high OGTT uptake and high rates of presentation to clinic for GDM care

Fig. 4

Mechanism map of clinical management for participants screening positive for GDM

Fig. 5

Revised logic model summarizing proposed intervention changes to address inconsistent clinical management of GDM