One platform. Infinite configurations.
mindLAMP is a modular digital health platform backed by 120+ peer-reviewed publications. The same platform supports entirely different studies and clinical workflows, with data stored in a uniform schema for cross-study comparison.
Why most digital health tools fail
Most digital health tools are built for single studies, creating barriers to reproducible science.
Incompatible Data
Each study builds its own app with unique data formats. Results can't be compared and infrastructure investment is wasted.
Consumer Apps Lack Rigor
Popular wellness apps lack research-grade data capture, clinical workflow integration, and the transparency research requires.
Expertise Gap
Even good platforms fail without digital phenotyping experience. Teams struggle with study design and avoiding pitfalls that cause data loss.
mindLAMP solves all three. Not just as software, but as a platform with expert support and 7 years of continuous clinical operation.
Why teams choose mindLAMP
Truly Modular
Configure activities, schedules, study groups, app layout, and phone/wearable sensor data collection without writing code.
Proactive Quality
Real-time monitoring catches issues before data loss. Troubleshoot proactively.
Uniform Data
All configurations produce the same schema. Compare across studies and reproduce methods.
Open Source
Inspect, modify, and extend the code. Adapt as your needs evolve.
10 Languages Supported
English, Spanish, French, Hindi, German, Italian, Korean, Danish, and Chinese.
Flexible Deployment
Shared infrastructure, dedicated instances, or self-hosted for data residency requirements.
See how it works
Configure Your Study
Use the researcher dashboard to design exactly what participants experience. Rather than hard-coded study logic, mindLAMP represents studies as configurations of reusable building blocks.
Choose Your Data Sources
Capture both what participants tell you and what their behavior shows. Select which sources to enable for each study group.
What participants complete
Background sensor collection from phone & wearables
Customize the Participant Experience
Tailor every aspect of how your study runs
Uniform Data Schema Across All Projects
Despite infinite configuration options, all mindLAMP data is stored in a standardized schema. This enables cross-study comparison and cumulative science.
Explore the data model →The Participant Experience
Participants engage through a user-friendly iOS and Android app with five configurable tabs. You decide which tabs to enable and what content appears in each.
Feed
Daily schedule of activities to complete
Learn
Educational tips & modules
Assess
Surveys & cognitive tests
Manage
Wellness tools & journaling
Portal
Personal data & progress
Analytics with Cortex
Cortex is a Python library that transforms raw sensor data into meaningful behavioral features. Use it to monitor data quality, run standardized analyses, and generate customized reports.
Monitor Data Quality
Track sensor collection and identify issues in real-time
GPS Collection Heatmap
Visualize coverage by hour and day
Sampling Rate Monitoring
Track against target thresholds
Catch sensor issues, permission problems, and engagement drops before losing data.
Extract Behavioral Features
Transform raw sensor streams into research-ready metrics
Generate Custom Reports
Create visualizations for dashboards, patient portals, or clinical handouts
Data quality tracking with completion gauges
Longitudinal symptom trends (PHQ-9, GAD-7)
Feature correlation matrix
Passive data correlated with active symptoms
Swipe to view report examples
For participants: Understand patterns and track progress
For clinicians: Identify concerning changes between visits
For researchers: Export data for deeper analysis
Proven across diverse contexts
120+ peer-reviewed publications across 50+ sites demonstrate that the modular approach works.
AMP SCZ
43 sites, 5 continents
2,600+ youth at clinical high risk for psychosis
Multi-language EMA + passive sensing in 9 languages
PREDiCTOR
Mount Sinai + IBM Research
Youth (15-30) seeking mental health care
AI prediction using smartphone + clinical interview data
Digital Clinic
Beth Israel Deaconess
Depression & anxiety patients
7 years of continuous clinical operation
SHARP
Boston, Bengaluru, Bhopal
Adults with schizophrenia
Relapse prediction via 12-month monitoring
CAPTURE-AD
Butler Hospital
Older adults (60-77) with/without MCI
90% passive data capture rate
SMART-A
Beth Israel Deaconess
MCI and mild Alzheimer's patients
6 novel cognitive tasks for early AD detection
momLAMP
Brigham & Women's Hospital
Women with postpartum anxiety
8-week CBT/ACT with high engagement
Safeguard
Henry M Jackson Foundation
U.S. Army soldiers
Life skills training for suicide prevention
Research Domains
Selected Research Findings
Relapse Prediction
Anomaly detection achieved clinically significant prediction of symptom exacerbation, with GPS-derived mobility showing strongest signal.
Cohen et al., 2023Convergent Validity
App-based mood ratings correlated r=0.80 with clinician-administered assessments.
Torous et al., 2019Participant Engagement
Studies report 60-80% survey completion rates across diverse populations over multi-week protocols.
Multiple studies, 2018-2024Who it serves
Research Teams
- Real-time data quality monitoring
- Multi-site consistency across 50+ locations
- Standardized schemas for cross-study comparison
- Cortex analytics pipeline for behavioral analysis
Clinical Programs
- Spot concerning patterns before crisis
- Data-informed conversations with patients
- Track progress with objective evidence
- Dashboards highlight who needs attention
Participants
- In-your-pocket accessibility to studies & interventions
- Personalized reports
- See how behaviors connect to mood
- Understand trends over time
- Review reports with care team
How we support you
The mindLAMP Core team provides expert support from study design through analysis.
Consult
Map your goals to configuration options
Design
Optimize protocol based on prior studies
Configure
Technical configuration to align with institutional requirements
Monitor
Track quality and engagement in real-time
Support
Ongoing troubleshooting and assistance
The Core team at Beth Israel Deaconess Medical Center has supported projects across diverse domains, bringing operational expertise so you can focus on your research.
Get started
Request a Consultation
Discuss your needs, see examples from similar projects, and determine fit.
Schedule Free ConsultationExplore Documentation
Review configuration options, analytics, API schemas, and open-source code.
Browse Documentation