Patients & caregivers
Share what happened, what made it harder, what helped, what is happening now, and what you wish the system understood.
Patient-aligned lived-experience intelligence
Health in the wild, starting with patients and caregivers.
PatientStories.ai is opening small alpha listening cohorts beginning with Type 1 diabetes, while also exploring GLP-1 patient journeys. We start with stories, not surveys, then organize lived experience into privacy-respecting insight.
Research insights, not data sales.
No identifiable patient data sales.
No raw story exports.
Published prior art: PatientStories.ai publicly documents its semantic-resolution, adaptive-engagement, privacy-processing, and telemetry-informed architecture to discourage overly broad patent enclosure of patient-centered workflows. Read the disclosure.
Alpha listening cohorts
Built around patients, caregivers, and the stories healthcare keeps missing.
Early participants will help shape PatientStories.ai before it grows. The first focus is Type 1 diabetes lived experience, with GLP-1 patient journeys emerging as a second signal area because so much real-world experience is scattered across comments, forums, and private conversations.
Type 1 diabetes
Capture failure points, device friction, food surprises, sleep disruption, emotional load, safety moments, and between-visit management.
GLP-1 journeys
Explore real-life use, dose changes, food shifts, GI burden, social discomfort, persistence, stopping, and the practical workarounds people discover.
Health in the wild
The lived reality before healthcare has a field for it.
Structured data tells us what healthcare already knows to measure. The wild reveals what people are actually living through: workarounds, tradeoffs, social embarrassment, treatment friction, emotional load, and the small decisions that shape whether a therapy works in real life.
Before the survey
Patients often describe signals before anyone has turned those signals into a checkbox, endpoint, or field in a database.
Before the visit
The most useful context may emerge between visits, close to the moment patients are managing burden, uncertainty, and adaptation.
Before the rework
Earlier patient-language intelligence can help teams see protocol burden, adherence risk, and support gaps before they become expensive surprises.
Why it matters
Patient experience becomes operational risk when assumptions meet real life.
Clinical data can show what happened. PatientStories.ai helps explain what patients were living through when it happened — in the wild, outside the neat boundaries of forms, visits, and expected answer choices.
Burden signals
Identify the daily effort, complexity, and friction that can shape study participation and treatment experience.
Patient language
Capture how patients actually describe symptoms, tradeoffs, confusion, relief, and behavior change.
Journey context
Connect condition history, treatment path, support, access, goals, and daily reality in one usable frame.
Better questions
Surface experience patterns early enough to improve protocol thinking, support design, and development decisions.
Highest-pain buying moments
Where patient insight prevents costly rework.
PatientStories.ai is built for the moments when the patient voice stops being a nice-to-have and becomes a development signal.
Moment 1
Protocol Development
Identify burden, care friction, endpoint relevance, visit-design risk, and real-world treatment context before protocol assumptions harden.
- Patient burden mapping
- Visit and task friction
- Endpoint relevance signals
Moment 2
Adherence Drop-Off
Understand why participants disengage, miss visits, delay tasks, or drift from expectations by capturing lived-experience signals directly from the journey.
- Participant fatigue
- Device and diary friction
- Support and access barriers
Moment 3
Amendment Pressure
Separate isolated complaints from recurring patterns before making expensive changes, helping teams understand what is actually broken.
- Pattern confirmation
- Burden prioritization
- Decision support context
Safety-aware patient intelligence
Built outside the trial stack. Informed by real-time clinical operations.
PatientStories.ai is not intended to replace a sponsor’s regulated clinical, safety, EDC, eCOA, pharmacovigilance, or trial master file systems. That separation is intentional.
From biometric telemetry and Clinical Decision Support to lived-experience signal.
The roots of PatientStories.ai trace back to Diabetech and early work in remote biometric telemetry, home-based disease management, Clinical Decision Support, and real-time patient-generated data workflows.
That work proved that meaningful patient signals do not have to wait for the next office visit. PatientStories.ai extends the same straight-through processing mindset into patient experience: capture the experience close to the moment it happens, preserve context, structure the signal, and make patterns visible sooner.
Biometric telemetry can show what changed. Clinical Decision Support can help organize what action might be considered. Patient narrative explains what it meant — the burden, behavior, care friction, tradeoffs, support gaps, emotional load, and daily decisions behind the signal.
Current position
The architecture could support prospective, real-time observational research under appropriate governance, including IRB oversight where required. That is not the default commercial model. PatientStories.ai is positioned as a safety-aware patient-experience intelligence layer outside the regulated system-of-record stack.
Safety Signal Awareness
Recognize when narratives may contain safety-relevant content, including possible AEs, SAEs, SUSARs, product complaints, worsening symptoms, or treatment-related concerns.
Human Review Pathways
Use AI-assisted detection to support structured review and escalation logic while keeping safety-sensitive interpretation under human oversight.
Data Integrity & Traceability
Design around consent clarity, timestamps, source preservation, version control, audit-conscious workflows, and responsible handling of patient-submitted content.
Standards-Informed Design
Informed by the principles behind the Declaration of Helsinki, GCP, ICH E6(R3), FDA 21 CFR Part 11, patient data safety, and practical patient journey UX.
How the platform works
From open narrative to structured patient intelligence.
Traditional surveys assume the right questions are already known. PatientStories.ai starts in the wild: patients begin with what they remember clearly, then the platform organizes the story into patterns that pharma teams can use.
Patients start with the story
A recent day, a difficult pattern, a treatment tradeoff, a workaround, or something no one seems to understand.
Guided prompts add context
Follow-up modules help structure burden, behavior, treatment journey, support, access, and daily reality.
Curation turns stories into signal
Patterns are organized into usable insight without stripping away the patient language that makes them valuable.
Outputs
Curated deliverables for sponsor teams.
We sell curated research insights — not identifiable patient data, raw narrative exports, or participant-level datasets. Outputs are designed for clinical development, medical affairs, patient engagement, and commercial insight teams.
Cohort Insight Reports
Curated summaries of patient experience patterns, burden signals, unmet needs, and subgroup differences.
Fully Matrixed Cohort Maps
Structured cohort maps that reveal how patient experience clusters across treatment journey, burden, behavior, support, access, and care friction — helping pharma teams identify actionable segments, unmet needs, and better questions earlier.
Signal Maps
Visual maps of recurring issues such as adherence barriers, treatment tradeoffs, side effects, device friction, emotional load, and care access gaps.
Patient Language Intelligence
The words patients actually use to describe symptoms, tradeoffs, confusion, success, fear, relief, and daily adaptation.
Protocol Risk Briefs
Patient-centered summaries that flag design assumptions likely to create burden, confusion, disengagement, or avoidable rework.
Amendment Context Packs
Rapid synthesis to help teams understand whether emerging friction reflects isolated feedback or a broader patient-experience pattern.
Trust model
We sell research insights — never patient data.
PatientStories.ai is built around a simple commercial boundary: participants share stories so their lived experience can reveal patterns, gaps, burdens, and unmet needs. Pharma and research partners receive curated, privacy-respecting insight outputs — not identifiable patient data, raw story exports, or participant-level datasets.
That distinction is central to the model. The value is in structured findings, cohort patterns, burden maps, patient-language themes, experience segments, unmet-need signals, and sponsor-ready reports derived from responsible analysis.
Who is behind this? PatientStories.ai is led by Kevin L McMahon. His professional background is available as a public evidence site so partners can evaluate the operating history, remote monitoring lineage, clinical operations experience, and credibility behind this effort.
Research Insights, Not Data SalesCurated intelligence is the product. Identifiable patient data is not.
Clear consentPlain-language participation and use expectations.
Aggregated outputsInsight reports and cohort summaries, not raw identity exposure.
No raw exportsNo default handoff of raw narratives or participant-level datasets.
Exploratory intelligenceBuilt to inform better questions, not replace regulated evidence.
Alpha interest / partner inquiry
Help shape what PatientStories.ai becomes.
For patients, caregivers, advocacy organizations, research partners, and pharma teams interested in lived-experience cohorts, Type 1 diabetes, GLP-1 patient journeys, or patient-aligned insight.