AI for Qualitative Analysis: LARC Uptake in Bangladesh

Primary keyword: qualitative analysis of LARC uptake. Researchers and program teams seeking to understand why long-acting reversible and permanent contraceptive methods (LARC/PM) remain underused in rural Bangladesh need contextual, multilevel evidence and scalable ways to synthesize it. According to the PLOS One article by Shoma and Barden-O’Fallon (published 25 August 2026), qualitative interviews in Cumilla district revealed knowledge gaps, fear-driven embodied experiences, patriarchal gatekeeping, religious stigma, and health-system failures as core drivers. This post refracts those PLOS One findings through an AI-enabled qualitative research lens and shows how thematic, cross-segment, and frequency analyses can turn 28 in-depth interviews and 9 key informant narratives into program-ready insights.

Key Takeaways

According to the PLOS One study (Shoma & Barden-O’Fallon, 25 August 2026), low LARC/PM uptake in rural Cumilla is driven by interacting individual fears and community- and system-level constraints, not by lack of efficacy of the methods themselves. The PLOS One study combined 28 in-depth interviews and 9 key informant interviews to map multilevel barriers. PLOS One documents concrete statistics and lived quotations that are extractable for program design.

28 in-depth interviews (22 women, 6 men) and 9 key informant interviews were conducted between 21 January and 20 February 2023, according to PLOS One (published 25 August 2026).
PLOS One reports that Cumilla had 13.6% LARC/PM use based on 2022 Directorate General of Family Planning data, and that national LARC/PM share declined from 12.1% in 1991 to 8% in 2022.
PLOS One quotes participants directly, for example: "Look, sister, we are uneducated people. We don’t know or understand these methods" (W 02), and a provider: "Most women who come for IUD removal complain of bleeding problems" (P 04).
PLOS One identifies five socio-ecological levels (individual, interpersonal, community, institutional, health-system) that together explain low uptake and point to multi-pronged interventions.

What Happened: Methods and core findings from the PLOS One study

Answer: The PLOS One study used purposive qualitative sampling and thematic analysis to identify multilevel barriers to LARC/PM uptake in Cumilla, Bangladesh.

According to the PLOS One article (Shoma & Barden-O’Fallon, 25 August 2026), researchers conducted 28 in-depth interviews with married people and 9 key informant interviews with service providers and one religious leader during 21 January–20 February 2023 to reach thematic saturation.

According to PLOS One, the study applied Braun and Clarke’s thematic analysis and a socio-ecological model to code transcripts that were transcribed in Bengali and translated to English to preserve quotations and context.

According to PLOS One, core findings included: (1) individual-level knowledge gaps and embodied side-effect experiences, (2) interpersonal male-dominated decision-making and mother-in-law gatekeeping, (3) community-level stigma, son preference, migration effects and religious objections, (4) institutional problems such as brief counselling, provider bias and privacy deficits, and (5) health-system shortages and low provider incentives.

Findings Snapshot

Date / Period	Metric	Value (from PLOS One)	Implication
1991 → 2022	Share of LARC/PM nationally	Declined from 12.1% (1991) to 8% (2022)	Program reversal suggests supply and demand shifts; requires system-level review (PLOS One, 25 Aug 2026).
2022	Cumilla LARC/PM use	13.6% (DGFP data cited in PLOS One)	Study site selected for persistently low uptake within Chattogram Division (PLOS One, 25 Aug 2026).
21 Jan–20 Feb 2023	Qualitative sample	28 IDIs (22 women, 6 men) + 9 KIIs	Sufficient to reach saturation for women and providers according to the authors (PLOS One, 25 Aug 2026).
2022	Contraceptive prevalence	National coverage rose from 7.7% (1975) to 64% (2022) (cited in PLOS One)	High overall coverage masks method-mix gaps favoring short-acting methods (PLOS One, 25 Aug 2026).

Implications for researchers and program teams

Answer: Researchers should design mixed-methods studies that link thematic drivers to measurable outcomes and programs should combine rights-based counselling with community engagement.

According to PLOS One, individual-level fears such as beliefs that implants "move around the body" or that ligation "causes infertility" are prevalent and are grounded in vicarious embodied experiences rather than abstract misinformation, so qualitative nuance matters for messaging.

According to PLOS One, interpersonal influences (15 of 22 women reported husbands had final say) and community-level norms (son preference, religious objections, stigma) indicate that single-focus demand-generation campaigns will be inadequate without male engagement and faith-leader involvement.

According to PLOS One, institutional failures (brief counselling sessions under 5 minutes, privacy deficits, and provider coercion) require system-level remedies that include provider training, supervision, and grievance mechanisms tied to service delivery targets.

How Evidano Helps: AI tools mapped to PLOS One problems

Problem: Rich qualitative transcripts but slow synthesis

Solution: Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents.

Evidano feature mapping: import the 28 IDI and 9 KII transcripts, run automated thematic coding, surface frequency counts for fears (e.g., infertility, device migration), and export quota-based codebooks for program briefs.

Why it matters: According to PLOS One, fear-driven themes are anchored in specific quotations and frequencies; Evidano preserves quotations and links them to codes so teams can quote sources like PLOS One accurately in proposals.

Problem: Need to compare subgroups (women vs men vs providers)

Solution: Evidano offers cross-segment analysis and co-occurrence networks to show which fears cluster with which demographics.

Evidano feature mapping: run co-occurrence of codes (e.g., "fear of infertility" co-occurring with "mother-in-law influence") to prioritize interventions by audience.

Why it matters: PLOS One documents divergent knowledge levels (implant known by 20/22 women, IUD by 9/22); Evidano makes such counts reproducible and transparent for funders and implementers.

Problem: Rights violations and consent issues need documentation

Solution: Evidano supports secure storage, PII redaction, and tagged excerpts for ethical audit trails.

Evidano feature mapping: tag statements of non-consensual insertion or refusal to remove methods and generate an extractable report for policy teams while preserving participant anonymity.

Why it matters: PLOS One reports cases of coerced insertion and refusal to remove implants; Evidano helps programs document and act on these incidents without compromising confidentiality.

Problem: Rapid knowledge translation for local stakeholders

Solution: Evidano auto-generates summaries, visualizations (word clouds, hierarchical code trees), and downloadable excerpts for community meetings.

Evidano feature mapping: create one-page evidence briefs that include verbatim quotes (attributed, anonymized) such as "Most women who come for IUD removal complain of bleeding problems" (P 04) to anchor discussions with religious leaders and field staff.

Why it matters: PLOS One emphasizes the need to engage faith leaders and husbands; succinct, evidence-based briefs reduce misinterpretation and enable targeted dialogue.

Further resources

Learn more about how these capabilities work in practice on the Evidano features page.

For secure transcription and PII redaction concerns raised by fieldwork, see Evidano’s speech-to-text and data security pages.

FAQ: qualitative analysis of LARC uptake

How many interviews did the PLOS One study use and when were they conducted?

Answer: The PLOS One study conducted 28 in-depth interviews and 9 key informant interviews between 21 January and 20 February 2023, as reported in PLOS One (25 August 2026).

Supporting detail: The 28 in-depth interview sample included 22 married women and 6 married men, and the KIIs included family planning providers and one Imam, which the authors say reached thematic saturation for women and providers.

What are the top three qualitative themes that programs should prioritize?

Answer: According to PLOS One, prioritize (1) addressing embodied fear and side-effect management, (2) engaging male decision-makers and mothers-in-law, and (3) fixing institutional counselling and consent practices.

Supporting detail: PLOS One reports method-specific fears (e.g., implant bleeding, IUD discharge), male-dominated decision-making (15 of 22 women noted husbands decide), and provider issues such as brief counselling under 5 minutes.

Can AI help convert qualitative quotes into program metrics?

Answer: Yes, AI-enabled qualitative research platforms can convert coded quotations into frequency metrics and segment comparisons while preserving context.

Supporting detail: The PLOS One study demonstrates the value of counting method familiarity (implant known by 20 of 22 women); Evidano and similar tools generate these counts automatically and link them back to verbatim quotes for transparency.

Is the PLOS One study nationally representative?

Answer: No, the PLOS One study is a purposive qualitative study focused on Cumilla and is not nationally representative.

Supporting detail: The authors explicitly note that findings are context-specific to Cumilla district and that transferability should be considered in similar rural contexts; quantitative DHS data are needed to generalize.

Conclusion & Next Steps

Answer: Multilevel barriers documented in the PLOS One study require combined qualitative insight and scalable analysis to guide rights-based program change.

According to the PLOS One article (Shoma & Barden-O’Fallon, PLOS One, 25 August 2026), interventions should couple couple-centered engagement, faith-leader dialogue, targeted counselling that addresses embodied side effects, and accountability mechanisms for providers.

Next steps for research teams: replicate the study’s coding framework on larger samples, use cross-segment frequency analysis to prioritize interventions, and document rights-violations for remedial action.

If you want to convert interview transcripts and field notes into actionable priorities as the PLOS One authors recommend, Try Evidano for free.

Topics

qualitative analysis of LARC uptake
LARC PM uptake Bangladesh
AI-enabled qualitative research
thematic analysis family planning

Keep reading

Browse all articles