The extensive use of smart technology (smart phones & wearables) and vast amount of information they contain, has positioned remote devices and technology as massive database for behavioral, personal and social day-to-day activities. Harnessing smart devices into the clinical field has introduced new, real time, data sources that hold promise in characterizing clinical functioning and intervene remotely on a scale and timeframe that would have been unimaginable a few years ago. This promise is beginning to come to fruition as both digital technology and the underlying data models to use the massive amounts of data they collect rapidly advance. Remote characterization of clinical populations (known as digital phenotyping) and subsequent digital methods of intervention are highly relevant in post-terrorist attack environments where both civilians and responders are at risk for psychopathology, while the events and their aftermath typically introduce uncertainty that limits clinician’s ability to identify and intervene in person. Specifically, several clinical situations which characterize PTSD would be prevented and better understood, by employing a digital personalized model which is capable to predict when certain deviations from a patient’s usual behavior may lead, with high probability, to his or her health deterioration. Downloading an authorized monitoring app following mass traumatic events may enrich the clinical monitoring with an objective and continuous data sources for digital phenotype including passive data sources (i.e. location information, word use, keyboard use, social media & internet use, gyroscope movement, communication and diurnal variation patterns), along with active data sources (i.e. voice prosody, facial & eye coding, linguistic analysis, remote survey). Computational approaches in machine learning and artificial intelligence are used to derive clinical characterization and prediction based on these data sources, creating a clinically valid monitoring algorithm which can be used for early detection and intervention after mass traumatic scenarios. Such approaches hold promise both for identifying psychopathology and for promoting resilience. While such methods hold promise, significant work is needed to understand clinical risk based on digital signals and to develop coordinated logistical systems to deploy useful interventions.