Evidano is an AI-powered qualitative data analysis platform that ingests transcripts, runs thematic and cross-segment analyses, and exports visual reports for decision-makers. This post refracts a June 8, 2026 PLOS study through the lens of qualitative analysis of schistosomiasis training needs and shows how AI tools speed evidence-to-action for researchers and health program teams. You will get a compact summary of key gaps identified in Uganda (n=105 government health workers), a snapshot of what to measure, and a 6-step AI-enabled workflow to run the same needs assessment and produce stakeholder-ready outputs in days not months. For hands-on replication, see how Evidano ingests transcripts, runs thematic and cross-segment analyses, and exports visual reports that decision-makers can use immediately.
Key Takeaways
The workshops in Pakwach, Buliisa, and Mayuge (Oct 21, 22, 25, 2024) identified gaps in distinguishing current infection from chronic morbidity, fragmented referrals, and frequent lack of praziquantel and ultrasound expertise. The study used one-day district workshops with 105 government health workers and manual inductive thematic coding to surface operational barriers to facility-based schistosomiasis management. The AI-enabled workflow presented here reproduces the study outputs in days by ingesting transcripts and case files into Evidano and producing validated themes, cross-district comparisons, and stakeholder-ready reports.
{"points": ["Workshops in Oct 2024 engaged 105 government health workers across three districts to map case definitions, patient pathways, and resource needs.", "The study found core gaps: unclear case definitions for infection versus chronic morbidity, fragmented referral pathways, praziquantel stockouts, and limited ultrasound skills.", "Reproducing the assessment is feasible in days using a structured 6-step AI-enabled workflow: ingest, standardize, auto-code, analyze, visualize, and iterate."]}
Fast take + source
Workshops in Pakwach, Buliisa, and Mayuge (Oct 21, 22, 25, 2024) engaged 105 government health workers to map case definitions, patient pathways, and resource needs for intestinal schistosomiasis morbidity management, and the study reports major gaps in distinguishing current infection versus chronic morbidity, fragmented referrals, and frequent lack of praziquantel and ultrasound expertise.
{"points": "Original source: [PLOS Neglected Tropical Diseases", "Why it matters: Without standardized case definitions and routine facility data, severe morbidity is under-recognized and unmanaged.", "Quick win: Use structured case studies and targeted, practical trainings to align clinical language and referral steps."]}
Findings snapshot
| Item | Value | Source / Note |
|---|---|---|
| Workshops (dates) | Oct 21, 22, 25, 2024 | One-day workshop per district |
| Participants | 105 | Clinicians, nurses, lab techs, sonographers, district managers |
| Districts | Pakwach (23.8%), Buliisa (36.2%), Mayuge (40.0%) | Reported in study demographics |
| Gender balance | 68.6% male (72/105) | Study Table 1 |
| Key resource gaps | Praziquantel stockouts; limited ultrasound access; few trained sonographers | Workshop findings |
| Primary methods | Interactive case studies, pathway mapping, thematic analysis | Braun & Clarke approach |
Qualitative analysis of schistosomiasis training needs: what the study did
The authors ran three one-day district workshops in rural Uganda (Oct 2024). Sessions combined cohort summaries, an expert clinical case, small-group reviews of real SchistoTrack patient cases (examined Jan–Feb 2024), pathway mapping, anonymous feedback, and demonstrations (Kato-Katz microscopy, ultrasound). Notes taken in English were manually coded using inductive thematic analysis, two authors validated codes, and the authors consolidated themes.
{"points": ["Outcome: three core themes, gaps in case definitions/diagnostic language, fragmented patient pathways, and limited training/resources.", "Practical nuance: many facilities used low-sensitivity wet mounts for diagnosis; ultrasound interpretation and abdominal palpation skills were sparse.", "Implication: MDA reduces infection but does not resolve periportal fibrosis, facility-based case management thus needs different tools and training."]}
Implications for researchers, program leads & UX teams
For researchers & evaluators
Researchers should measure both current infection and chronic morbidity indicators, for example ultrasound findings, hypersplenism, and variceal bleeding, and capture them in HMIS-friendly codes. Use mixed qualitative datasets (workshop notes, case narratives, facility inventories) to triangulate gaps, and apply thematic coding to surface operational barriers beyond prevalence numbers.
For health program & policy teams
Health program and policy teams should standardize case definitions and simple grading (mild/moderate/severe) that lower-level staff can apply reliably, and embed these into training and HMIS templates. Prioritize low-cost capacity fixes: include praziquantel on facility essential-medicine lists, fund basic ultrasound and sonographer mentorship, and formalize referral-feedback loops.
For UX / implementation designers
UX and implementation designers should build job aids and one-page ultrasound interpretation guides that reconcile language across clinicians, sonographers, and lab techs, because the study flagged a language disconnect. Prototype a minimal patient-pathway flowchart and test in 2–3 facilities before scaling.
How Evidano helps (mapped to these gaps)
Problem: scattered notes, manual coding
Evidano ingests workshop notes, scanned case files, and survey spreadsheets and runs rapid thematic and frequency analyses so teams get validated themes (for example 'ultrasound skills' and 'drug stockouts') in hours not weeks.
Problem: inconsistent diagnostic language across cadres
Use Evidano hierarchical codes and subcodes to harmonize terms (sonographer versus clinician descriptors), export a shared codebook, and re-run analyses to check inter-cadre consistency.
Problem: need cross-segment comparisons
Evidano cross-segment analysis compares responses by district, facility level, or cadre (for example HCIII versus HCIV) to surface targeted training priorities and resource mismatches.
Problem: stakeholder-ready outputs
Evidano can generate word clouds, co-occurrence networks, and clickable quote exports for training modules and policy briefs, and the platform encrypts data and never uses uploaded data to train third-party models.
Problem: follow-up data collection
Evidano can run AI-avatar interviews to autonomously collect structured follow-up data from facilities after a training, and then re-analyze to measure shifts in language, confidence, and reported practices.
AI-enabled checklist: reproduce this assessment in 6 steps
Step 1: Gather inputs, for example workshop notes, audio (transcribe in Evidano with PII redaction), case-study PDFs, and HMIS extracts.
Step 2: Standardize, import or create a codebook in Evidano, and set segment variables (district, cadre, facility level).
Step 3: Auto-code and refine, run AI-assisted coding, review uncertain codings, and lock validated codes.
Step 4: Thematic and cross-segment analysis, generate theme frequencies, co-occurrence networks, and segment comparisons (for example sonographers versus clinicians).
Step 5: Visualize and export, build word clouds, hierarchical code trees, and a one-page policy brief with clickable source quotes for validation workshops.
Step 6: Iterate and measure, deploy AI-avatar follow-up interviews at 4–8 weeks to measure training uptake and changes in referral practice.
FAQ: schistosomiasis training needs
What were the main training gaps identified in the workshops?
The main training gaps were unclear case definitions distinguishing current infection from chronic morbidity, fragmented referral pathways, frequent praziquantel stockouts, and limited ultrasound and palpation skills. The study authors observed reliance on low-sensitivity wet mounts for diagnosis and sparse ultrasound interpretation skills across facilities.
Who participated in the district workshops and when were they held?
One hundred and five government health workers participated in the workshops, which were held on Oct 21, 22, and 25, 2024, across the districts of Pakwach, Buliisa, and Mayuge. Participants included clinicians, nurses, lab technicians, sonographers, and district managers.
How can teams reproduce the study’s outputs quickly?
Teams can reproduce the study’s outputs in days by ingesting transcripts and case files into Evidano and following a 6-step workflow: gather inputs, standardize codes, auto-code, analyze themes and segments, visualize, and iterate with follow-up interviews. The checklist in this post maps each of those steps.
What immediate actions should health programs prioritize?
Health programs should prioritize standardizing case definitions into simple grading, adding praziquantel to facility essential-medicine lists, funding basic ultrasound mentorship, and formalizing referral-feedback loops. Embedding these actions into HMIS templates and short practical trainings will improve recognition and management of severe morbidity.
Conclusion, next steps and CTA
Pairing structured qualitative methods with an AI research platform dramatically cuts synthesis time and improves reproducibility for training needs assessments like the PLOS Uganda workshops. Reproduce the study’s outputs (themes, quotes, cross-district comparisons) in days by ingesting transcripts and case files into Evidano. Start a pilot: upload one workshop’s notes and run a thematic and cross-segment report to demonstrate immediate value to district health officers.
{"points": ["Reproduce the study’s outputs in days by ingesting transcripts and case files into Evidano.", "Start a pilot: upload one workshop’s notes and run a thematic and cross-segment report to show immediate value to district health officers."]}
Ready to try this workflow? Try Evidano for free or visit Evidano to learn more or contact the team about a free pilot on one workshop dataset and a stakeholder-ready report in under 7 days.