About Nasken Health
Nasken Health is the healthcare initiative of Nasken Inc, based in Boston. We build AI-assisted remote patient monitoring, post-discharge risk identification, and health data interoperability for small and rural clinics — the settings where monitoring is hardest to staff and clinical data is hardest to move.
Our mission is to bridge the gap between traditional care delivery and intelligent digital systems by securely analyzing patient-generated data between visits. We use privacy-preserving machine learning to support better engagement, early risk detection, and personalized care.
Our earlier work includes an AI-supported therapy session summarization tool that assists clinicians in tracking progress, improving outcomes, and enhancing collaboration across care teams.
AI-Powered
Machine learning for real-time clinical insights
Patient-Centered
Enhancing engagement and therapeutic outcomes
Privacy-First
Privacy and consent as design constraints
Why Post-Discharge Monitoring Matters
The weeks after discharge are where recovery is decided and where clinical visibility is thinnest. This is the research base for our current work.
Sources: Centers for Medicare & Medicaid Services (2023); Farahani et al., Journal of Hospital Medicine (2026); De Lathauwer et al., European Journal of Heart Failure (2025); Scientific Reports (2023).
Evidence Behind Our Earlier Work
This is the research base for our earlier journaling work. Structured journaling and patient-generated data improve self-awareness, support emotion regulation, and give clinicians richer context between sessions.
Sources: American Psychiatric Association (2024); JAMA Network Open (2022); Smyth et al., JMIR Mental Health (2018); ResearchGate PGHD Review (2020); MDPI Social Sciences (2023).
Blogs & News
Research and federal guidance relevant to our current and earlier work.
Current work — post-discharge monitoring and interoperability
HL7 FHIR and federal interoperability
Federal overview of the FHIR standard, its role under the 21st Century Cures Act, and why it underpins health data exchange.
Read MoreRemote biometric sensing after discharge
Systematic review and meta-analysis of 39 studies examining readmission and mortality outcomes for patients monitored after leaving hospital.
Read MorePredicting readmission from post-discharge activity
Randomised trial testing whether remotely monitored activity patterns improve 30-day readmission prediction over models built from discharge data alone.
Read MoreWhich RPM components actually work
Meta-analysis comparing remote monitoring programme components against hospitalisation and mortality outcomes in heart failure.
Read MoreTelemonitoring high-risk patients after discharge
Prospective cohort study of home telemonitoring and follow-up for high-risk patients, measuring readmissions and emergency visits.
Read MoreWhere remote monitoring did not help
Trial across 19 hospitals in which some remote-response strategies produced fewer days at home than usual care for older post-discharge patients.
Read MoreEarlier work — journaling and patient-generated data
How journaling supports mental health
Overview of evidence and practical ways journaling can reduce stress, clarify thoughts, and support therapy.
Read MoreWhat is Patient-Generated Health Data (PGHD)?
Federal overview of PGHD, its sources, and how it augments clinical decision-making and care coordination.
Read MoreNasken Health joins NVIDIA Inception Program
Nasken Health has been accepted into NVIDIA’s global startup program supporting AI innovators. This collaboration accelerates our mission to build trustworthy, privacy-preserving AI for healthcare.
Read MoreConversational agents for mental health: scoping review
Systematic synthesis of mental-health chatbots, use cases, outcomes, and safety considerations.
Read MorePatient-generated data improves patient-provider communication
Study showing how introducing PGHD changes communication behaviors and care interactions.
Read MoreApp-based interventions for depression: clinical evidence
Randomized-trial evidence on smartphone-based interventions as part of depression care.
Read MoreEarly Results & Traction
These figures come from our earlier work: an early pilot deployment validating our journaling and AI-assisted insight platform with clinicians and behavioral health researchers.
Technology
Our stack combines AI precision, privacy-preserving design, and interoperability — built for small and rural clinics.
Post-discharge risk identification
Identifying which patients need attention in the weeks after discharge, when clinical visibility is thinnest.
Interoperable Architecture
FHIR/HL7-based data exchange enabling seamless integration with EHR systems and clinical dashboards.
Privacy-First Infrastructure
Privacy and consent are design constraints for the platform rather than features bolted on later.
Adaptive Insight Engine
Continuous learning loops that refine outputs through clinician feedback while maintaining versioned model governance and transparent evaluation.
Built for Healthcare
Every layer of our system is designed for compliance, workflow alignment, and patient safety.
Contact & Partnerships
We welcome conversations that advance digital health innovation. Reach out to explore collaboration or partnership opportunities.
General Contact
For all other inquiries or to discuss how Nasken Health can support your organization's digital health initiatives
Contact UsSubscribe to our Newsletter
Stay updated on Nasken Health’s research, product releases, and digital health insights.
By subscribing, you agree to receive occasional updates. You can unsubscribe anytime.