Digital Phenotyping and Dynamic Monitoring of Adolescents Treated for Cancer to Guide Intervention: Embracing a New Era

Adolescents diagnosed with and treated for cancer represent a particular vulnerable patient population with unique and complex medical and psychosocial needs that extend beyond the completion of treatment (1–4). These cancer patients are in the most critical phases of their development (5–7), with brain, body, mind, and social environment in constant transformation conferring vulnerability to some individuals and resilience to others. Adolescence is characterized by a heightened incidence (and first onset) of various mental illnesses (8–10). Cancer during adolescence influences peer relationships, changes mood and behavior, interferes with cognitive functioning, educational achievement, and increases the risk for the onset of psychopathology (11, 12). Furthermore, treatment is often accompanied by numerous physical and psychological symptoms such as nausea, vomiting, sleep disturbance, fatigue, pain, changes in body weight and body-image (2), treatment-induced psychosis, depression, and anxiety. Importantly, peer interactions in young cancer patients is often suddenly interrupted putting them at a higher risk for the development of emotional and behavioral problems. Even though many of these concerns remain largely unattended because of a lack of timely detection and management (13, 14), recent data indicate a growing awareness of the specific needs of this patient population suggesting that a concerted effort should be made to develop age-appropriate resources that could help them manage their illness and its treatment (15). When asked, adolescents indicate five domains of concern: 1) physical, emotional, behavioral, and mood problems related to treatment; 2) psychosocial issues; 3) present and future adjustments once the therapy has finished; 4) transition, organization, and management of survivorship; and 5) need to be better connected, involved, and informed (16–20). Given this, it is vital to capture, as early as possible, the biological, psychological, emotional, behavioral, and social modifications in young cancer patients to expand our day-to-day understanding of the factors affecting their vulnerability. Most importantly, reviews and guidelines based on best practice stress the fact that cancer in adolescents does not always have chronic negative outcome especially if we understand which individuals are at heightened risk (20). Any issue in the five domains of concern listed above must be detected early to put timely and preventive measures into place (21). Adolescent cancer patients represent an enormously heterogenous group and while most somatic treatments are accompanied by the development of acute or chronic unwanted effects (2, 4), we currently lack the capacity to distinguish individual trajectories leading to increased vulnerability or resilience. A paradigm shift is essential to detect the distinct clinical pathways of high-risk individuals (22–24). Current innovative digital approaches to patient care and monitoring offer a unique opportunity to create predictive models of individual vulnerability based on the integration and interdependencies of diverse sources of information. The analysis of the data contained in these platforms allow the projection of potential outcomes and disease trajectories, identifying those patients that are progressing from generic vulnerability to becoming at high risk for a negative event. Digital tools may have numerous potential benefits compared to traditional assessments: they are non-invasive, ecological, do not demand extra efforts, and provide continuous access which offers timely understandings of the emotional, behavioral, cognitive, and treatment related changes. Also, while not all studies underline a clear benefit, some of them indicate that they are unrestricted by time and place, and offer immediate access to data and intermediate endpoints, reduce stressful visits, remove barriers to access to care (fear, isolation), stimulate patient empowerment, and, most importantly, help in the identification of high-risk patients and their risk stratification (23–26). As a result, the integration of various digital tools in a “toolbox,” would offer a concrete opportunity to modify, replace, or accompany the current more categorical approach and shift to a multimodal dimensional methodology (27, 28) in which evidence is gathered from different domains, ranging from subtle neurocognitive disfunction (29–33) to biomarkers. Ultimately, the multidimensional continuous recording of data and especially their dynamic relationships would become an integral part of the care plan and serve as specifiers of an high-risk status (34, 35).