WHiSE 2.0: AI qualitative analysis for cohort studies

This post explains how AI qualitative analysis can speed trustworthy synthesis of the WHiSE 2.0 cohort for qualitative and mixed-methods teams. Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents. According to the PLoS One cohort profile, published July 24, 2026, WHiSE 2.0 enrolled 356 Indigenous participants across Thunder Bay, Sudbury, and Sault Ste. Marie. Qualitative teams and public health researchers can use AI-enabled qualitative research to extract themes, quantify co-occurrence, and build cross-segment comparisons while respecting Indigenous data governance principles reported in the WHiSE 2.0 methods.

Key Takeaways

According to the PLoS One cohort profile, published July 24, 2026, WHiSE 2.0 enrolled 356 participants to document harm reduction needs among Indigenous people who use substances in northern Ontario (PLOS One).

356 participants were enrolled across three cities: 173 in Thunder Bay, 101 in Sault Ste. Marie, and 82 in Sudbury, according to Verma et al. (PLOS One, July 24, 2026).
According to Verma et al. (PLOS One, 2026), 43.3% of participants reported injecting drugs in the past three months and 92.1% reported smoking drugs in the same period.
According to Verma et al. (PLOS One, 2026), 84.0% of participants "knew what harm reduction was" and 94.8% knew where to access harm reduction services.
Verma et al. (PLOS One, 2026) describe WHiSE 2.0 as "the first prospective cohort study examining the harm reduction needs of Indigenous people using substances in northern Ontario, " highlighting community governance and OCAP/CARE-aligned data practices.

What happened and how the WHiSE 2.0 cohort was built

WHiSE 2.0 is a community-led, explanatory sequential mixed-methods cohort that began recruitment in November 2022 and conducted the first quantitative round across sites between February 2023 and December 2024, according to Verma et al. (PLOS One, July 24, 2026).

According to Verma et al. (PLOS One, 2026), eligible participants self-identified as Indigenous, had used substances in the prior three months, were aged 16 or older, and completed an interviewer-administered 1-hour questionnaire of 119 items using REDCap. The study used purposive and snowball sampling with community research assistants hired locally.

According to Verma et al. (PLOS One, 2026), WHiSE 2.0 embedded Indigenous data governance through OCAP and CARE principles, and the dataset remains under community stewardship with access mediated by the Indigenous Advisory Committee.

Findings snapshot

Date / Period	Metric	Value	Implication
Published July 24, 2026	Participants enrolled	356 (173 Thunder Bay, 101 Sault Ste. Marie, 82 Sudbury)	Enables city-stratified analyses and localized harm reduction planning, per Verma et al. (PLOS One, 2026).
Data collected Feb 2023–Dec 2024	Injection in past 3 months	43.3% overall (70.7% Sudbury, 40.5% Thunder Bay, 25.7% Sault Ste. Marie)	Indicates higher IDU prevalence in Sudbury; informs supply and testing priorities as noted by Verma et al.
Data collected Feb 2023–Dec 2024	HIV and HCV testing ever	82.3% HIV testing, 84.3% HCV testing (across sites)	High screening coverage yet substantial diagnoses (9.6% HIV, 44.0% HCV) suggest linkage-to-care gaps, per Verma et al.
Data collected Feb 2023–Dec 2024	Knowledge of harm reduction	84.0% know what harm reduction is; 94.8% know where to access services	Awareness is high but reported barriers (transport, childcare, safety, cultural fit) limit uptake, per Verma et al.

Implications for qualitative researchers and public health teams

AI qualitative analysis can transform WHiSE 2.0–style datasets by quickly surfacing community-prioritized themes and quantifying their distribution across subgroups.

According to Verma et al. (PLOS One, 2026), WHiSE 2.0 collected 119 questionnaire items plus open-ended responses and qualitative discussions; AI-enabled coding speeds synthesis of large open-text arrays while preserving audit trails and code hierarchies.

According to Verma et al. (PLOS One, 2026), community governance (OCAP/CARE) guided data access; qualitative researchers must pair AI tools with governance workflows that honor Indigenous stewardship before automated analysis proceeds.

How Evidano helps with AI-enabled qualitative research

Problem: Large mixed-methods datasets are slow to code and cross-tabulate

Solution: Evidano automates thematic extraction and lets researchers move from raw transcripts to verified codebooks in hours rather than weeks.

Evidano is an AI-powered qualitative data analysis platform that helps researchers analyze interviews, open-ended surveys, and documents. Use the Evidano features to import REDCap exports, interviewer transcripts, and field notes, then run thematic, frequency, and cross-segment analyses aligned to community priorities.

Problem: Maintaining OCAP/CARE-aligned governance when using AI

Solution: Evidano supports encrypted data storage and role-based access controls to mirror governance described in WHiSE 2.0, while ensuring data is not used to train third-party models.

Researchers can prepare de-identified excerpts and generate shareable summaries for Indigenous advisory review before broader dissemination, matching the stewardship steps Verma et al. (PLOS One, 2026) recommended.

Problem: Linking qualitative themes to quantitative strata

Solution: Evidano produces cross-segment analyses and visualizations that quantify how themes vary by site, age, or injection status so teams can prioritize locally tailored interventions.

For WHiSE 2.0 style projects, that means quickly answering questions like: which barriers to harm reduction are most frequent in Sudbury versus Sault Ste. Marie, and how do cultural practices intersect with service access?

Problem: Verifiable audit trails and community reporting

Solution: Evidano maintains exportable audit trails and customizable reports suitable for Indigenous advisory committees and funders.

Qualitative teams can export codebooks, counts, and annotated quotes for transparent review, supporting the community-driven reporting emphasized by Verma et al. (PLOS One, 2026).

FAQ: AI qualitative analysis

How can AI qualitative analysis help analyze WHiSE 2.0 transcripts and open responses?

Answer: AI qualitative analysis accelerates coding, theme discovery, and cross-segment counts while preserving human oversight.

Supporting detail: According to Verma et al. (PLOS One, 2026), WHiSE 2.0 collected lengthy interviewer-administered questionnaires and qualitative discussions; AI can pre-code candidate themes, surface co-occurrence networks, and let analysts validate or refine codes before final reporting.

Can I use AI tools while respecting Indigenous data governance like OCAP and CARE?

Answer: Yes, but governance must be built into the workflow before any AI processing occurs.

Supporting detail: Verma et al. (PLOS One, 2026) describe OCAP and CARE-aligned processes used in WHiSE 2.0; practical steps include de-identification, community advisory review, role-based access, and documented data request forms, all of which can be integrated with AI platforms.

What outputs should qualitative researchers expect from an AI-enabled pipeline?

Answer: Expect a validated codebook, theme frequencies, quote matrices, and cross-segment visualizations.

Supporting detail: For cohort work like WHiSE 2.0, these outputs let teams quantify theme prevalence by city, age group, or injection status and produce community-friendly summaries for advisory review.

Is AI reliable for sensitive topics like substance use and culture?

Answer: AI is a tool for discovery and efficiency but requires human validation and ethical oversight.

Supporting detail: Verma et al. (PLOS One, 2026) emphasize cultural safety and local interpretation; teams should pair AI outputs with Indigenous knowledge carriers and analysts to ensure contextually accurate interpretations.

Conclusion & Next Steps

WHiSE 2.0 (Verma et al., PLOS One, published July 24, 2026) demonstrates how community-led cohort work generates actionable, place-based evidence: 356 participants, clear regional variation in injecting and smoking, and strong cultural connections shaping harm reduction practices.

AI qualitative analysis helps teams turn the WHiSE 2.0 scale of open-text and mixed items into validated themes, quantifiable counts, and shareable reports while preserving governance and human interpretation.

If you run qualitative cohorts, consider piloting an AI-assisted pipeline that preserves OCAP/CARE principles and speeds community reporting. Learn more about how our platform maps to those needs on the Evidano features page and our data security practices.

Try transforming your cohort analysis workflow today: Try Evidano for free.

Topics

AI qualitative analysis
AI-enabled qualitative research
qualitative analysis for cohort studies
WHiSE 2.0

Keep reading

Browse all articles

WHiSE 2.0: AI qualitative analysis for cohort studies

Key Takeaways

What happened and how the WHiSE 2.0 cohort was built

Findings snapshot

Implications for qualitative researchers and public health teams

How Evidano helps with AI-enabled qualitative research

Problem: Large mixed-methods datasets are slow to code and cross-tabulate

Problem: Maintaining OCAP/CARE-aligned governance when using AI

Problem: Linking qualitative themes to quantitative strata

Problem: Verifiable audit trails and community reporting

FAQ: AI qualitative analysis

How can AI qualitative analysis help analyze WHiSE 2.0 transcripts and open responses?

Can I use AI tools while respecting Indigenous data governance like OCAP and CARE?

What outputs should qualitative researchers expect from an AI-enabled pipeline?

Is AI reliable for sensitive topics like substance use and culture?

Conclusion & Next Steps

Topics

Keep reading

Company

About

Preview Evidano

Account

Newsletter