David C. Mohr - US grants

[unreadable] DESCRIPTION (provided by applicant): Major depressive disorder (MOD) is common, with 12-month prevalence rates estimated at between 6.6- 10.3%. A large literature has established that depression can be effectively treated using pharmacotherapy and/or psychotherapy. Several studies have found that given a choice, about two-thirds of depressed patients prefer psychotherapy or counseling over antidepressant medication. While psychotherapy is both effective and ostensibly desirable, a variety of barriers exist both to initiating and maintaining psychotherapy. Only about 20% of all patients referred for psychotherapy ever follow-up. Of those who do initiate psychotherapy, nearly half drop out prior to completion of treatment. Administering psychotherapy over the telephone may overcome many barriers associated with failure to initiate treatment and attrition from treatment. A number of recent studies have shown that telephone- administered treatments are effective at reducing depression, well accepted by patients, able to extend treatment to patients who experience significant barriers including disabilities. Furthermore, telephone administered psychotherapies are likely associated with low rates of attrition, compared to treatments delivered face-to-face. This study will compare a 16-week telephone-administered cognitive behavioral therapy (T-CBT) intervention to 16 weeks of face-to-face CBT (FtF-CBT). It is hypothesized that 1)T-CBT will produce lower rates of attrition compared to FtF-CBT, 2) intent-to-treat analyses will show T-CBT to produce significantly greater reductions in depression compared to FtF-CBT, in the sample initiating treatment and 3) the greater reductions in depression associated with T-CBT will be fully mediated by attrition. This research has the potential to produce a manualized T-CBT program that could extend treatment to many populations who are currently unable to access care. [unreadable] [unreadable] [unreadable]

DESCRIPTION (provided by applicant): The aim of this pilot grant is to develop a telemental health intervention for depression that integrates web-based cognitive behavioral skills training with therapist motivational support and outreach, and to develop procedures for a larger Phase III clinical trial. Major depressive disorder (MDD) is common, with 12-month prevalence rates estimated to be between 6.6-10.3% 1, 2. While many depressed patients state they would prefer psychological treatment to pharmacotherapy, substantial barriers to care exist, including cost, practical barriers such as time constraints and transportation, emotional barriers such as stigma, decreased motivation associated with depression itself, physical disability, and lack of availability of services. The development and validation of telemental health interventions as a means of overcoming these barriers has been widely called for by the NIMH, the 2003 President's New Freedom Commission on Mental Health, and leaders in the field of mental health. Two telecommunications technologies have been explored to deliver telemental health interventions: telephone-administered psychotherapy and web based internet therapy. Telephone administered psychotherapy has repeatedly been shown to produce significant reductions in depression as well as very low rates of attrition (mean attrition rate = 7.5%). Internet-based cognitive behavior therapy (ICBT), which provides automated CBT skills-training, has considerable potential. However, outcomes have been only small to moderate, in part because many people do not return to the website. To date, research has examined telemental health interventions using primarily one methodology or the other. While each of these technologies has advantages, intervention programs relying primarily on one technology are limited by the disadvantages of that technology. We are proposing to develop an integrated telemental health intervention (ITHI) that utilizes I-CBT, telephone support and e-mail. The first 12 months would focus on the development of the I-CBT website. The remainder of the study would pilot three treatment arms, ITHI, I-CBT and a waitlist control. All assessment and monitoring procedures would also be piloted.

DESCRIPTION (provided by applicant): Depression is common and disabling. Advances in telecommunications have greatly increased the possibilities for delivering behavioral interventions. Unfortunately, the initial results in this emerging field indicate that much work remains before viable systems can be implemented clinically. The mission of this Center is to develop and pilot novel systems of care that can provide efficacious, scalable, cost-effective, patient friendly technology assisted behavioral interventions (TABIs) for the treatment and prevention of depression. The Center's model proposes that adherence and efficacy can be enhanced by increasing support from humans, creating greater connectedness to patients in their environments, and developing new interfaces that are more conducive to promoting complex behavior change. To this end, we will propose a Technology Development Unit that will develop and refine three new technologies that address each of these areas, two pilot trials that will test novel interventions in the treatment and prevention of depression, and two measurement projects that will develop and evaluate metrics. The Technology Development Unit will 1) refine mobile phone technology that can continuously monitor patient behavior, environmental context, and mood, and can reach out to engage the patient at critical moments in his/her environment, 2) refine an online peer network that is specifically designed to activate participants to provide support and encourage accountability among its members, and 3) develop programmable virtual humans to support interpersonal skills training. Two pilot trials will 1) evaluate these technologies in the context of an internet treatment for depression in adults and 2) evaluate these technologies in the context of an internet treatment for prevention of depression in adolescents. Measurement projects will, using data collected in the pilot trials, evaluate measurement in two critical areas for TABIs: adherence and cost-effectiveness.

B.3.2 Principal Research Core. DRPs are designed as pilot RCTs aimed at developing procedures and data to support larger R-01 submissions for full clinical trials. DRP #1 (Yrs 3-5): TABI for the treatment of depression in adults. This project will build on an existing Internet Intervention, moodManager (37). Each of the technologies developed in the IMPs will be incorporated and tested In a full factorial design. DRP #2 (Yrs 3-5): Ben Van Voorhees, MD. TABI for the prevention of depression in youth. This project will build on the internet Intervention, CATCH-IT (48,49). Each of the technologies developed in the IMPs will be incorporated and piloted In an RCT with youth, ages 13-18, who are at risk for depression.

The organization and aims of the Center are guided by our conceptual framework. As displayed in Fig. 1, two critical goals for TABIs remain the enhancement of efficacy and adherence. Our Center Model is built upon models proposed by Eysenbach (35) Ritterband (36) and Mohr (37) . We propose three factors that affect efficacy and adherence in internet interventions. (38). 1) Human Support: There is growing evidence that support from clinicians can improve adherence to internet interventions far more than can non-human support (e.g. automated e-mails) (37,39-42). Human beings appear to have a unique ability to elicit a sense of accountability in adhering to behavioral treatments from their fellow humans (43). Web 2.0 allows a care system to harness networked users (i.e. peers), and to engineer interactions that support both adherence to treatment (e.g. logging in) as well as the quality of use (44). 2) Connectedness: This factor reflects the confinuity of contact between the user and the TABI care system. Telecommunicafions technologies (e-mail, telephone, mobile phones) permit more confinuous contact with users, which can extend more fully into the user's environment. Connectedness adds two potenfial improvements over simple internet interventions. First, they allow push funcfions that can contact pafients, rather than relying on patients to contact the website. Second, they can potenfially permit more frequent monitoring (e.g. ecological momentary assessment; EMA) ofthe user in his/her environment and intervenfions that are fimed at crifical moments. 3) Presentation Characteristics: This factor typically refers to features of technology (e.g. use of audio and video, or degree of tailoring in a website) that may affect how the user interacts with it. Technologies are becoming available that permit much more interacfive, simulated environments that have the potenfial to provide unique avenues for learning. This factor reflects the continuity of contact between the user and the TABI care system. Telecommunications technologies (e-mail, telephone, mobile phones) permit more continuous contact with users, which can extend more fully into the user's environment. Connectedness adds two potential improvements over simple internet interventions. First, they allow

DESCRIPTION (provided by applicant): Major depressive disorder (MDD) is prevalent and imposes a very high societal burden in terms of cost, morbidity, quality of life, and mortality. While psychological treatments are both effective and acceptable to patients, a variety of barriers exist both to initiating and completing psychotherapy. Telemental health has been proposed as a method of overcoming barriers to treatment. Research has focused primarily on two formats: the telephone and the Internet. Telephone-administered cognitive behavioral therapy (T-CBT) appears to be equivalent to face-to-face CBT in efficacy, but produces fewer dropouts. However, T-CBT's success in improving access could also significantly increase costs for healthcare providing organizations. Internet CBT (iCBT) is typically a web-based program that provides didactic training and interactive tools to teach CBT skills. iCBT guided by brief coach or therapist via telephone is substantially less costly and more cost effective and standard face-to-face treatment, but produces more moderate improvements in depression and produces comparatively high levels of attrition. Developing a treatment delivery model that integrates T-CBT and iCBT holds the promise of harnessing the advantages of each medium, while minimizing the disadvantages. A stepped care model, in which patients begin with iCBT and are stepped up to T-CBT only if they do not improve, is a potentially useful framework for achieving a successful integration. We have proposed a randomized controlled trial (RCT) that will recruit 310 patients with MDD, and randomly assign them to stepped care or T-CBT. Patients will remain in treatment for 20 weeks, or until full remission is reached, at which point treatment would be discontinued. It is hypothesized that 1) the stepped care treatment will not be inferior to T-CBT and 2) stepped care will be more cost-efficient.

DESCRIPTION (provided by applicant): Major depressive disorder (MDD) is common and imposes a very high societal burden in terms of cost, morbidity, suffering, and mortality. While primary care is the de facto site for treatment of MDD, outcomes in primary care are poor. Two principal reasons for the poor outcomes in primary care are poor patient adherence to antidepressant medications (ADMs) and the failure of physicians to provide guideline-congruent care. This problem is aggravated by a lack of communication between patients and the care team. A growing body of research indicates that primary care-centered strategies aimed at enhancing guideline-congruent care have not been effective. Interventions aimed at improving adherence in the patient have been successful in changing patient adherence behavior; however these frequently fail to improve depression outcomes, particularly when there is no intervention on the physician side to encourage optimization of ADMs. The most effective strategies address both provider and patient behaviors, usually through the use of a case-manager who monitors and supports patient adherence and response to treatment, and provides actionable feedback to the PCP. However, case-managers have not been widely implemented in primary care settings. Recent developments in information and communications technologies (ICT) have opened new opportunities to improve health and mental health care, and to link patients and their providers. Our proposal harnesses these advances to develop and pilot the medLink system. ADM adherence will be passively measured using an electronic pill dispenser, which is connected to a mobile smartphone via Global System for Mobile Communications (GSM), so that targeted, timely reminders can be provided when the patient fails to take the ADM. When the patient is adherent, the patient will not be bothered with reminders. Depressive symptoms and side-effects will be periodically monitored weekly via the phone. Every 4 weeks, or if indicated (e.g intolerable side effects or urgent situations), primary care teams will receive notifications via the electronic medical record that include a summary of patient data on treatment response and side effects, guideline- congruent treatment recommendations based on patient data and a recommendation to contact the patient, if indicated. Simultaneously, a similar message will be provided to the patient via short message service (or text), including feedback, possible treatment options, and a recommendation to contact the physician's office. Thus, both the patient and care team will be activated to provide, request and adhere to guideline-congruent care. The aim of this proposal is to develop and pilot the medLink system. Development will employ an iterative user-centered approach. The pilot trial will compare 12 weeks of the medLink system to a treatment as usual control among primary care patients with MDD initiating ADM treatment. Outcomes will include patient adherence to ADM, physician adherence to treatment guidelines, and depression.

DESCRIPTION (provided by applicant): The primary aim of this proposal is to develop and evaluate the use of state of the art machine learning approaches within a mobile intervention application for the treatment of major depressive disorder (MDD). Machine learning, a branch of artificial intelligence, focuses on the development of algorithms that automatically improve and evolve based on collected data. Machine learning models can learn to detect complex, latent patterns in data and apply such knowledge to decision making in real time. The proposed intervention, called IntelliCare, will use ongoing data collected from the patient and intervention application to continuously adapt intervention content, content form, and motivational messaging to create a highly tailored and user-responsive treatment system. Behavioral intervention technologies (BITs), including web-based and mobile interventions, have been developed and are increasingly being used to treat MDD. BITs are moderately effective in treating depression, particularly when guided by human coaching via email or telephone. However, lack of personalization and inability to adapt to patient needs or preferences, which results in a perceived lack of relevance, contributes to poorer adherence and outcomes. IntelliCare will be designed as a mobile application, but will be accessible via computer web browsers and tablets. The IntelliCare machine learning framework will use individual data obtained from use data (e.g., length of time using a treatment component), embedded sensors in the phone (e.g., GPS), and the user's self-reports (e.g., like and usefulness ratings of treatment components) to provide a highly tailored intervention that can learn from the patient and adapt intervention and motivational materials to the patient's preferences and state. Low intensity coaching will serve as a backstop to support adherence. This project will contain three phases. Phase 1 will involve the development of IntelliCare and its optimization through usability testing. Phase 2 will be a field trial of 200 users who will receive IntelliCare for 12 weeks. The field trial has two aims: first to complete usability testing and optimization of the treatment framework, and second to develop the machine learning models and algorithms. Phase 3 will subject IntelliCare to a double blind, randomized controlled trial, comparing it to MobilCare. MobilCare will be identical to IntelliCare except that it will use standard presentation and presentation, rather than machine learning, to provide treatment and motivational materials. We will recruit half the participants from primary care settings, as this is the de facto site for treatment of depression in the United States, and half through the Internet, which is the main portal to health apps. The application of adaptive machine learning analytics to a mobile intervention has the potential to create a new generation of BITs that could revolutionize the way that such interventions are conceptualized, designed, and deployed. These innovations would have broad consequences and could be extended a broader range of BITS, including web- based interventions, and to other interventions targeting a wide range of health and mental health problems.

Abstract Depression is common, costly, and a leading cause of disability. Assessment of behavior and experience related to depression has tended to rely on self-report and interview-based methods. Environmental momentary assessment inserts assessment into people's lives, but still requires active engagement by those being evaluated. We propose to develop and validate a mobile phone-based personal sensing system to detect depression and related behaviors that relies on sensor data that are collected continuously and unobtrusively. Because people tend to keep their phones with them, the mobile phone is an ideal sensing platform, as it can continuously collect data in the context of the individual's life with no ongoing effort on the part of the user. Such systems are already being used to detect simple behaviors, such as activity recognition and sleep quantification, which are more proximal to the sensor data. Aim 1 will develop markers for a broad range of behavioral targets related to symptoms of major depressive episode (MDE; anhedonia, negative mood, sleep disruption, psychomotor activity, fatigue, and diminished concentration) and related domains (e.g. social functioning, stress, motivation) across a representative sample of participants. Aim 2 will combine all behavioral targets using machine learning to 1) estimate MDE and symptom severity cross-sectionally, 2) identify transition from non-depressed to depressed states, and depressed to non-depressed states, and 3) predict MDE and symptom severity 4 and 8 weeks out. Aim 3 will seek to understand the complex relationships among behavioral targets and depression. We will accomplish this by enrolling 1200 representative participants, in six 4-month waves of data collection. Each participant will download software that collects a wide variety of sensor data (GPS, accelerometry, light, Bluetooth, phone usage, etc.) and an app that collects ecological momentary assessments (EMA). Following each wave we will develop algorithms for a subset of behavioral targets and features (a definition of raw sensor data that incorporates meaning, like translating GPS data into ?home?). Each algorithm will then be validated in the subsequent wave. After 5 waves (1000 participants), the set of all markers of behavioral targets and features will be combined using machine learning to detect and predict depression. This hierarchical approach extracts information from data at multiple levels, which ultimately is far more likely to succeed than relying solely on raw sensor data. The final wave will serve to replicate and validate the entire depression prediction model. This sensing platform is scientifically significant, as it will provide a fundamentally new tool for obtaining continuous, objective markers of behavior that are relevant to depression, as well as many other psychiatric and medical disorders. This project has the potential develop new understandings into the etiology of depression. It is clinically significant, as it will allow for continuous, effortless assessment of populations at risk for depression and ongoing evaluation during treatment.

Abstract This application proposes to establish an innovative, multi-disciplinary postdoctoral research training program focused on digital mental health) and technology across Northwestern University's Feinberg School of Medicine, School of Communication, and McCormick School of Engineering. The long-term goal of this program is to develop the field of digital mental health by providing the first NIMH-supported postdoctoral training program that integrates mental health (psychology, psychiatry, and behavioral science) and human- computer interaction (HCI; computer science, communication, engineering, design, and human factors) aimed at producing successful, independent investigators who will become leaders in this emerging field. Digital mental health as a field has not lived up to its potential to deliver mental health care cost-effectively to large numbers of people. Part of this failure is due to the largely siloed approach to research and training. This program will recruit a mix of fellows in clinical research and HCI. Fellows will develop core competencies in digital mental health, team science, research ethics, leadership, as well as other topics as needed such as implementation science or computer science. Fellows will also develop a working understanding of the methods and principles in the domain that the fellow is learning (e.g. behavioral science for HCI Fellows, HCI design methods for mental health specialists). Each trainee will be co-mentored by a faculty member who specializes in clinical mental health research and one specializing in HCI. At least 75% of the fellow's time will be spent in mentored research. These research experiences will be complemented by a weekly seminar, professional development activities, problem based learning, and workshops and other didactic experiences to cover basic knowledge. Fellows will also have access to the rich educational resources made available by Northwestern, including training in grant writing workshops, paper writing seminars, team science training, and other resources dedicated to career development. Our participating faculty mentors and advisors are leaders in their respective fields and come from 9 departments across 3 schools. We will admit 3 fellows each year for a two year fellowship. This program will be the first in the nation to jointly train mental health and technology specialists, and will serve as a model for the emerging field of digital mental health.

Abstract Technology-enabled services (TESs), which use web-based and mobile applications supported by low- intensity coaching or care-management, have shown great potential, with a large number of randomized controlled trials consistently demonstrating efficacy. However, the many attempts to implement these validated interventions into large value-based care systems have failed. There are two broad reasons for these failures. First, patients in real world settings simply do not use the tools that were developed in research settings. Second, TESs have not been designed to fit into the workflows in general medicine practices. This research project will use a comprehensive user centered design approach to engage patients, care managers (CMs) and physicians in the design of a TES?comprised of technologies, CM service protocol, and implementation plan?that can be successfully deployed in a collaborative care program in family medicine clinics. The overall TES will be designed to support the existing collaborative care model, facilitating the acquisition of ongoing depression assessments from patients and communication with prescribing physicians. The design innovation focus of this research project will be to design a patient app that is simple, usable, useful, and fits into the fabric of people?s lives. We will harness ongoing research efforts in our Center in personal sensing, which use passively collected data from mobile phones to identify behaviors relevant to depression in real time. To date, we have created algorithms that reliably identify GPS mobility patterns, physical activity, locations visited, sleep patterns, and in-phone communication patterns, all of which track behaviors related to depression. This project will design patient interfaces that can represent this sensed information to patients in ways that are easily understandable, and that nudge people to increase positive activities, decrease depressogenic behaviors, and explore the relationship between behaviors and mood. We will use a behavior activation framework for the design of the intervention protocol. The TES will also include a CM dashboard that provides visibility into patient app use, as well as communication tools that allow the CM to provide low intensity support to the patient and communicate with the physician around pharmacotherapy needs. The effectiveness and implementation of the TES will be evaluated in a roll out cluster randomized trial across 4 primary care clinics This project will be the first to integrate the emerging capabilities of personal sensing into intervention apps. The resulting TES has the potential to be the first that is usable by real world patients, fits into clinic workflows, and can be successfully implemented in a general medicine collaborative care program.

ABSTRACT The objective of the Healthcare System & Technology Design Core (`Design Core') is to adapt and extend new methods for the design, deployment and evaluation of technology-enabled services tailored for older adults with multiple chronic conditions (MCC) and their caregivers. We will translate innovative research in digital health, building to scale for sustainable implementation in diverse primary care practices. Significant enthusiasm exists for technologies to transform healthcare service delivery. It has been proposed that technologies can improve quality and reduce the cost of healthcare, increase a patient's capacity to successfully engage in treatment decision-making and self-care behaviors, improve communication with a primary care team, moving treatment outside of clinics into peoples' homes and deploy a variety of devices to help embed services into the fabric of peoples' everyday lives. Unfortunately, for all the evidence demonstrating that such technologies can work under controlled conditions, we have identified several failures of technology development and evaluation that hinder meaningful impact on healthcare services for older adults with MCC. The Design Core's goal is to spur research on the integration of technologies into healthcare services for older adults with MCC and their caregivers. Our specific aims are to: Aim 1 Provide expertise to investigators in the design, evaluation and implementation of technology-enabled services for older adults with MCC and their caregivers. Aim 2 Create a prototype technology-enabled service, designed for older adults with MCC and symptoms of anxiety or depression, to communicate more effectively with their clinicians. Aim 3 Develop and disseminate a methodology guide that summarizes best practices for applying user- centered design (UCD) to optimize technology-enabled services for older adults with MCC. The Design Core will become a national hub of expertise in the design and evaluation of technology-enabled services for older adults with MCC (Aim 1). We will extend CBITs' expertise accumulated over 8 years and 70+ projects to support the design, development, and evaluation of technology-enabled services. We will devise an MCC-specific technology design prototype through a `reference' project (Aim 2). We will then integrate our work with other leaders nationally, producing an initial guide for supporting the development of technology enabled services appropriate for primary care settings and among older adults with MCC (Aim 3).

Abstract Technology-enabled services (TESs), which use web-based and mobile applications for patients coupled with support from a care coordinator, have consistently been shown through randomized controlled trials to be effective at treating depression. However, attempts to implement TESs in healthcare settings have failed, primarily because neither real-world patients nor providers use the tools we develop and evaluate in research. This center addresses this research-to-practice problem through a multi-level strategy. At the research proposal (RP) level, we will design and evaluate TESs for depression in three unique medical settings that commonly manage depression. Each RP will include a unique design innovation. RP1 will design and evaluate a TES to support a primary care collaborative care program. The design innovation of RP1 will focus on integrating mobile phone sensing technologies to create simpler, more engaging patient tools. RP2 will design and evaluate a TES for a specialty obstetrics care setting for postpartum depression. The design innovation will focus on care manager-facing tools and processes that can simplify, organize, and automate workflows. RP3, set in a geriatric service, will focus on homebound older adults, for whom there are few treatment options. The design innovation will be to harness a voice-controlled intelligent personal assistant to support homebound older adults, with supports for family caregivers. At the research level, we will harness the three RPs to refine our Accelerated Create-to-Sustainment (ACTS) research framework, which aims to overcome the research-to- practice gap in several ways. ACTS integrates human computer interaction (HCI) methods to incorporate the voice of end users into the design and evaluation of the technologies, service protocol, and implementation plan for the RPs, thereby ensuring that the end product is usable, useful, and can be implemented. Core research design elements and measurements are consistent across the RPs, which will allow us to evaluate the ACTS framework across all RPs to validate the core research principles of the ACTS framework. With the help of our External Scientific Advisory Board, will use this experience to produce research guidelines for digital mental health research, and aggregate the knowledge gained about TES and organization features into a taxonomy that represents essential information for researchers and developers. We will achieve this this work through a highly interdisciplinary team, led by two PIs who are leading experts in experts in digital mental health and HCI (Mohr and Reddy), with additional expertise in medicine, implementation science, psychology, research methods, and statistics. Each of the RPs is co-led by the clinic or service chief and a researcher, thereby ensuring a deep collaboration between clinical service needs and research. Thus, this Center, by using a multilevel approach focusing on both the individual research projects and methodology, will produce the first TESs designed for implementation in real world healthcare settings, and will provide substantial and enduring contributions to research methodology that will improve the quality of science.

Abstract The Administrative Core will promote innovation and excellence within each research project and the Methods Core, and at the same time support and facilitate collaboration and integration across all components of the proposed P50 Center grant. The Administrative Core will build on the successful administrative structures developed by our P20 Developing Center grant, which launched the Northwestern University Center for Behavioral Intervention Technologies (CBITs), as well as on infrastructure available through Northwestern University. This proposed Center would extend CBITs areas of expertise to include design, human-computer interaction, and implementation science. The proposed Center will be advised by an External Scientific Advisory Board (ESAB) and an Internal Advisory Board (IAB). A Steering Committee, chaired by Drs. Mohr and Reddy, will include all Methods Core workgroup leaders and Research Project leads. The Steering Committee will provide guidance, direction, and organization for the Center. The Administrative Core will carry out a variety of functions in the proposed Center including: (1) facilitate and coordinate transdisciplinary research across Research Projects and Methods Core workgroups; (2) oversee the solicitation and review of pilot grants; (3) coordinate training; (4) communicate the Center's aims, achievements, activities, findings, and resources; (5) oversee Center evaluation procedures (6) oversee resource sharing; (7) carry out future planning; (8) develop the Center's research processes and products as a national resource; and (9) ensure sustainability and growth.

PROJECT SUMMARY Young adults aged 18-24 experience higher levels of mental health problems than any other adult age group. Over one quarter of all young adults living in the United States suffer from a mental health condition. Unfortunately, they are the adult age group who are least likely to seek or receive traditional face-to-face treatments such as in-person psychotherapy or pharmacotherapy. There is evidence that they are, however, interested in using digital mental health interventions (DMHIs), such as mobile and web-based apps, to support symptom self-management and skill building. While evidence suggests mental health apps can effectively reduce symptom severity, they require motivation from the user to open and use the app, which contributes to the high dropout rates. The primary method of addressing dropout has been the use of human coaching, which boosts engagement. SMS text messages arrive through the most commonly used app on the phone, and are therefore likely to be viewed. Initial work in text message interventions suggests good adherence, as effort is low, but effectiveness has been inconsistent. Messages can be perceived as off-target or impersonal, and it is difficult to convey more complex information. This project aims to address these problems by developing and piloting a personalized text messaging platform that uses machine learning to tailor SMS messages to an individual?s needs and preferences, and URL links to provide access to psychoeducational content to contextualize messages, when the length of that content exceeds the limitations of messages. This project will include a partnership with Mental Health America, the nation?s largest mental health advocacy organization. The primary goals of the project are to: (1) Develop an adaptive messaging service for young adults that personalizes messages and psychoeducational content to the needs and preferences of an individual, (2) Conduct a feasibility trial using a sequential multiple assignment randomized treatment (SMART) design, which will evalutate (a) the effectiveness of an adaptive, personalized messaging intervention in reducing engagement relative to a static version; and (b) whether human coaching results in greater symptom reduction and engagement, relative an unguided implementation. This project will, in the near term, allow us to determine the feasibility of this intervention, including whether our adaptive intervention affects treatment psychological and engagement targets, and reduces psychological distress. It will also provide preliminary information on the feasibility of a scalable model of targeted, low- intensity coaching for users who may require additional support above and beyond a fully automated intervention. This will prepare us for our longer-term goal of conducting a fully-powered randomized controlled trial of our adaptive intervention in an online community setting.