Addressing Challenges in Mental Health Care
Measurement
Mental health conditions are often subjective and rely heavily on self-report questionnaires, interviews, and observations, which can be inconsistent, infrequent, or influenced by bias. Many mental health symptoms fluctuate daily, and traditional clinical visits capture only snapshots of a patient’s experience, potentially missing critical trends. |
Access to Treatment
Access to traditional mental health care is limited by systemic challenges such as provider shortages, high costs, long wait times, stigma, and geographical barriers (e.g., rural or underserved areas). |
MindLAMP as the Solution
Measurement with MindLAMP
Increasing Access to Care with MindLAMP
|
Digital Phenotyping with MindLAMP
Toward supporting more transparent and ethical research, the need for better data collection, data processing, and return of results is clear. Data processing pipelines offer a productive focus, as they can support data from multiple apps and transform that data to support myriad visualizations. Cortex is an open-source data processing pipeline for digital phenotyping data, optimized for use with the mindLAMP apps. Cortex is designed to help teams (1) assess digital phenotyping data quality in real time, (2) derive replicable clinical features from the data, and (3) enable easy-to-share data visualizations. Cortex can process thousands of coordinates from the GPS phone sensor and transform them into a metric that reflects how much time a participant spent at home, appropriately named “hometime.”
|
Special Focus on Data Monitoring and Quality Dashboard/Metrics
This figure shows how many GPS data points are being collected over time. The beginning of the x-axis represents the very start of the day, 12 AM or 00:00 in 24-hour time. Each hour is represented as a square and given a gradient of blue, with the deeper blues representing more data points collected. Each row represents 1 day and starts at the top. Ideally, the user would want each square to be blue with a little star within.
|
This figure shows how many accelerometer data points are being collected over time. The x-axis represents the time of data point collection, and the y-axis represents the amount. Ideally, the user would want to see the blue line never drop below the red.
|
What is the LAMP Platform?The LAMP Platform is a neuropsychiatric research and clinical care management platform designed to help you run remote smartphone-based research studies that can include surveys (ecological momentary assessments), mobile cognitive tests, sensors (native to the smartphone and external), and digital interventions delivered via the smartphone. The LAMP Platform functions as 4 pieces, the App, the Dashboard, the Database, and Cortex. |
LAMP Platform Components
1. The mindLAMP App
The patient uses the native Android and Apple app for a variety of purposes customized to your needs. This can include taking real-time surveys, playing cognitive games, accessing helpful tips and resources, doing meditation and breathing exercises, etc; and when enabled and configured, the app can also collect sensor data from the mobile device's accelerometer, GPS, pedometer, and more in the background without interrupting the patient. It also collects metadata about the patient's use of the app, like how long certain questions took to answer in a survey, or which helpful tips they appreciated the most, and uploads the data securely to a server you or your organization owns (or the CORE hosts for you). All content (psychoeducation, surveys, interventions, and feedback) as well as sensors activated can be fully customized and toggled off/on. The CORE can support any use case desired from the app acting as a simple medication reminder to a customized after care support tool to a full digital phenotyping suite.
|
2. The Dashboard
Clinicians and Researchers can create, customize, and schedule activities for patients or participants to interact and receive notifications, and tap into near-real-time information about patients to better inform decision making. The dashboard also allows for unique interactive features for specialized research or clinical-specific use. Additionally, the dashboard now has a fully functional Data Portal for an in-depth and comprehensive view of all patient and participant data. The CORE can support custom dashboards and reporting or help with use of the flexible default.
|
3. The Database
The Database securely and chronologically indexes the data through the LAMP Protocol for programming and data science. It informs custom data analysis code in real-time that new patient data has arrived. Researchers can better build reusable tools, analysis pipelines, and conduct reproducible science, knowing that others around the globe using the LAMP Platform can easily work with their data or replicate their unique study. The CORE can provide support to host your own database or host your data in a private and secure manner.
4. Cortex
The Cortex data analysis pipeline is designed to easily hook into the Database and extract important and clinically useful secondary data features, such as sedentary behavior, time spent at home, device/screen usage, sleep estimates, and much more, from the terabytes of raw data. It can trigger custom just-in-time adaptive interventions and produce useful interactive visualizations viewable by patients and clinicians. The CORE can run default or custom analysis on your data.
LAMP Features
Open Source and Sharable Code Base
The open-source nature of mindLAMP ensures that anyone across the world can work with, expand, and use the platform. The code is available at https://github.com/BIDMCDigitalPsychiatry, and already clinical research teams in Canada and Australia are using our version of the platform to create their own adapting versions. This represents a healthy software ecosystem that ensures findings from research on mindLAMP are real-life tools that others will engage with and develop further.
Flexible and Customizable BackendThe flexible and customizable backend of mindLAMP offers important benefits. Each site is able to easily run the common study protocol in terms of data capture, but also to add new site-specific questions or schedules if desired. The backend of mindLAMP allows each site to store its own data centrally or locally, meaning that the app can be run in a distributed manner as needed to comply with local, state, federal, and international laws. As necessary, mindLAMP can also be deployed from a central site to support teams not wishing to locally administer it. |
|
LAMP Use Cases
Clinical Care
mindLAMP is unique in that it is more than a research tool and is already deployed in clinical care. These clinical use cases for mindLAMP offer a direct pathway for translational research to have an immediate impact in care. The clinical use of mindLAMP also informs its development and ensures that research and clinical needs find synergy. mindLAMP can also support learning through offering on demand psychoeducation, and management through just-in-time adaptive interventions (e.g., elevated anxiety scores trigger a mindfulness activity in the app). There is also a patient portal to review all data captured and ability to chat within the dashboard. These features can be enabled depending on the clinical or research needs.
Current National and International Studies
mindLAMP already has a track record of successful uses in many diverse clinical research settings. The app has received local IRB approval and has been deployed not only in its Harvard/Beth Israel Deaconess ProNET home site but also in India, Canada, Australia, and the United Kingdom. Current research projects are also underway at other US sites including the Mayo Clinic, Boston University, Los Angeles Department of Mental Health, The Massachusetts Psychosis Network for Early Treatment, ProNET site Northwell Health, and others. The ability of each of these sites to use mindLAMP reflects its flexible nature, practical value, and ease of use.