Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents. Researchers and program teams analyzing help-seeking in underserved, justice-involved populations can use AI to speed coding, extract relational patterns, and test intervention hypotheses. The PLOS One study (published July 30, 2026) provides a rigorous qualitative framework based on 50 interviews collected between November 1, 2023 and July 31, 2024, showing how desire, ability, and context interact across social networks to shape help-seeking for mental health and substance use. This post translates the PLOS One findings into practical, AI-enabled qualitative research steps and shows how teams can use Evidano to operationalize them.
Key Takeaways
According to PLOS One (published July 30, 2026), help-seeking for mental health and substance use among people in contact with the criminal justice system is driven by an interaction of three domains: desire, ability, and help-seeking context, all of which are shaped by social networks.
- The PLOS One study (published July 30, 2026) conducted 50 in-depth interviews between November 1, 2023 and July 31, 2024, with 23 participants in LA1 and 27 in LA2.
- Background prevalence cited in the PLOS One article (July 30, 2026) reports over 40% meeting criteria for a substance use disorder, more than 10% for major depressive or psychotic disorders, and 75% for any personality disorder in similar justice-involved samples.
- The PLOS One authors concluded on July 30, 2026 that “help-seeking is not an individual behaviour, but strongly affected by relational influences” and recommended multi-level interventions targeting networks and context.
- Participant testimony in PLOS One (July 30, 2026) included statements such as "I have dealt with it for almost twenty odd years by myself… I don’t like going to doctors because I think they are a waste of time" (participant P12) and "you just kind of can’t get away from the social" (participant P13).
What Happened and how it was measured
Answer-first: The PLOS One study (published July 30, 2026) used framework analysis of 50 semi-structured interviews collected with participant-aided sociograms to identify influences on help-seeking among justice-involved people living in the community.
The PLOS One research team interviewed 50 participants (23 in a largely rural LA1 and 27 in a deprived urban LA2) between November 1, 2023 and July 31, 2024 and transcribed interviews verbatim for framework analysis.
According to PLOS One (July 30, 2026), the analytic framework used three top-level categories (desire to seek help, ability to seek help, and help-seeking context) with relational subthemes embedded within each category to reflect social network effects.
PLOS One (July 30, 2026) combined qualitative interview data with social network mapping software (Network Canvas) to capture who network members were, relationship length, and perceived support, and analysed data using NVivo-assisted framework coding.
Findings Snapshot
| Date | Metric | Value | Implication |
|---|---|---|---|
| July 30, 2026 | Publication | PLOS One | Provides framework linking desire, ability, and context with relational influences for help-seeking |
| Nov 1, 2023–Jul 31, 2024 | Interviews collected | 50 participants (23 LA1, 27 LA2) | Sufficient qualitative depth to identify network-level themes across two contrasting localities |
| July 30, 2026 | Background prevalence (reported in article) | Over 40% SUD; >10% major depression/psychosis; 75% personality disorder (from cited literature) | Highlights high clinical need in justice-involved populations and the public health importance of improving help-seeking |
Implications for qualitative researchers and program teams
Answer-first: The PLOS One framework (published July 30, 2026) implies that qualitative researchers should code for relational and contextual themes in addition to individual attitudes when studying help-seeking.
Researchers following the PLOS One approach should collect network data alongside narrative interviews, code at multiple levels (individual, tie, network, community), and explicitly report dates, sample sizes, and recruitment contexts as the PLOS One authors did.
Program teams designing interventions should note the PLOS One recommendation (July 30, 2026) for multi-level strategies that target networks (trusted messengers, peer support design), service accessibility (flexible appointments), and community stigma.
Ethics note: If applying this method to mental health or substance use research, teams should follow the participant protections described in PLOS One (July 30, 2026), including pseudonymisation and data access controls; findings are for research and service design, not clinical diagnosis.
How Evidano Helps
Problem: Large volumes of interview text and scattered network data slow synthesis
Answer-first: Evidano converts transcripts, survey text, and sociogram outputs into a single analyzable corpus to accelerate synthesis.
Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents, and it ingests transcripts and social-network exports so teams can code theme-by-theme across data types.
Use case: upload interview transcripts and Network Canvas CSVs, then run thematic extraction to surface recurring relational phrases (for example, "don’t like going to doctors") that PLOS One (July 30, 2026) highlighted as core barriers.
Problem: Detecting relational patterns across a 50-interview dataset
Answer-first: Evidano automates co-occurrence and cross-segment analysis to reveal how network beliefs and norms cluster with help-seeking behaviours.
Evidano supports hierarchical codes, co-occurrence networks, and cross-segment frequency analysis so researchers can test PLOS One-style frameworks (desire, ability, context) across localities and subgroups.
Practical feature link: See the platform's features for thematic, frequency, and cross-segment analyses that map directly to the PLOS One analytic goals.
Problem: Transcription accuracy and sensitive data handling
Answer-first: Evidano offers secure transcription with custom dictionaries and PII redaction to match the ethical safeguards used by the PLOS One team.
Evidano's transcription and encryption workflows reduce manual cleanup and maintain data governance for sensitive justice-involved research.
Teams can export coded matrices that mirror the PLOS One matrix approach (cases as rows, themes/sub-themes as columns) to support team review and audit trails.
FAQ: ai qualitative analysis help-seeking
How can AI accelerate thematic analysis of interviews about help-seeking?
Answer-first: AI speeds initial code generation and surface-level thematic grouping so human analysts can focus on interpretation and relational nuance.
According to PLOS One (July 30, 2026), the depth of relational themes requires human judgement; AI tools provide candidate codes and co-occurrence maps that researchers then refine to match the study’s framework.
Practical tip: Use AI to propose initial codes, then double-code a subset manually as the PLOS One team did with independent coders to ensure reliability.
What network data should I collect to apply the PLOS One framework?
Answer-first: Collect who network members are, perceived attitudes toward help-seeking, relationship length, and perceived support because PLOS One (July 30, 2026) used those variables to surface relational influences.
The PLOS One study (published July 30, 2026) combined sociograms collected with Network Canvas and interview narratives to connect network structure with norms and resource flow.
Practical tip: Export Network Canvas or similar CSVs and ingest them into your qualitative platform to join tie-level attributes with verbatim quotations.
Can AI identify stigma and epistemic mistrust in transcripts?
Answer-first: AI can flag language patterns associated with stigma and mistrust, but human review is required to interpret context and avoid false positives.
PLOS One (July 30, 2026) describes 'epistemic mistrust' as a network-rooted phenomenon; AI keyword and sentiment signals can highlight candidate excerpts that analysts then evaluate for meaning and stance.
Ethical note: For stigma-related coding, combine automated flags with researcher validation and ensure participant consent and data protection as in the PLOS One protocol.
Conclusion & Next Steps
AI-enabled qualitative research makes it practical to scale the PLOS One approach (published July 30, 2026) by joining interview text and network data to map desire, ability, and contextual influences on help-seeking.
The PLOS One study (July 30, 2026) shows that relational factors in social networks are central; AI helps surface those relational signals at scale while preserving researcher-led interpretation.
If your team needs to replicate PLOS One-style framework analysis or build multi-level evaluations, Evidano can ingest transcripts and network exports, run thematic and cross-segment analyses, and keep sensitive data secure.
To start testing the approach on your data, Try Evidano for free.