Our lab has established a technical framework for the development and deployment of digital health applications that operate across mobile and web platforms. Applications are built using the Flutter/Dart framework, which supports cross-platform development for iOS, Android, and web, allowing us to maintain efficiency in code management while deploying to multiple environments. Separate codebases are implemented for patient-facing applications and provider or research team dashboards to ensure that functionality is optimized for each user group.
Flowchart of technical framework of devices and platforms.
The backend architecture is hosted on Google Cloud Platform and makes extensive use of Firebase services. Firebase Authentication provides secure identity management, Firestore enables real-time storage of pseudonymized data, and Firebase Hosting supports rapid deployment of front-end interfaces. Cloud Functions are used to manage backend logic, including data validation, automated triggers, and just-in-time adaptive intervention delivery. BigQuery is employed as the centralized data warehouse for aggregation and large-scale analysis, while Cloud Scheduler and Firebase Cloud Messaging support task orchestration and participant reminders.
Protected Health Information is stored exclusively within REDCap, which functions as the system of record under institutional governance. REDCap also integrates with external modules such as Twilio for secure messaging. All cloud resources are provisioned within the Weill Cornell Medicine enterprise environment, where system monitoring, patching, and compliance are managed centrally to meet HIPAA and IRB standards.
Wearable devices such as Fitbit Sense 2 are integrated through the Fitbit API, with server-to-server data transfer into BigQuery. This provides a continuous stream of passive activity and physiological measures, which can be combined with active ecological momentary assessments delivered via the mobile applications.
In collaboration with Dr. Nili Solomonov, we have developed the TREE-Connect intervention that reduces the number of sessions of the Engage and Connect psychotherapy for depressed older adults and adds an machine-learning powered prompt to promote adherence. The TREE-Connect app incorporates prediction models in a just-in-time digital intervention to promote adherence to psychotherapy. We are currently proposing to test the intervention in a clinical trial that is part of our renewal proposal for our Weill Cornell ALACRITY Center. Our goal with the TREE-Connect app is to extend reach, reduce patient and therapist burden, and enhance adherence. Our prediction models and the just-in-time digital intervention can also be added to any existing psychotherapy.
In collaboration with Dr. Dimitris Kiosses, we developed the WellPATH tablet app that implements WellPATH, a personalized mobile intervention for depressed older adults with suicidal ideation. WellPATH is a novel tablet-app intervention that aims to reduce suicide risk by employing simplified, personalized, easy to administer and use, cognitive reappraisal strategies during emotional crises and at scheduled brief training sessions. The WellPATH intervention is based on the assumptions that using personalized cognitive reappraisal techniques during an emotional storm, and practicing these techniques during scheduled training sessions will increase cognitive reappraisal ability and reduce suicide risk.
WellPATH app homescreen, negative emotion list and personalized trigger list.
In collaboration with Dr. Daniel Shalev, MD and Dr. Irina Mindlis, PhD, MPH from the Division of Geriatrics and Palliative Medicine, we have developed EMA-PAL, a web-based intervention to improve how symptoms are monitored and managed in outpatient palliative care. EMA-PAL collects real-time symptom reports from patients using short, secure surveys and provides interactive feedback through simple visualizations. Clinicians can view these data on a provider-facing dashboard, supporting timely, data-informed conversations during clinical visits. Our goal with EMA-PAL is to reduce recall burden, capture under-assessed symptoms such as anxiety and depression, and enhance communication between patients and providers. By gathering data in the moment, EMA-PAL promotes more accurate symptom assessment and strengthens shared decision-making.
EMA-PAL is being tested in an exploratory study, Ecological Momentary Assessment to Improve Symptom Management in Palliative Care. Patients and providers participate in interviews and co-design focus groups to shape the platform and provide feedback on its usability. The study aims to understand the feasibility and acceptability of EMA in palliative care, and to create a patient–clinician dashboard tailored to this setting.
EMA-PAL allows patients and providers to track real-time progress and tailor treatment discussions.
