The power of combining traditional data with direct patient feedbacks.

The combination of traditional data like clinical data or lab results with real world evidence based data from patient feedbacks on the go is incredible valuable. This offers the potential for earlier intervention and less follow-up costs.

Evidence-based research leads the way for daily practice.

A full range of data already shows the value of PROMs / PREMs in various indications. One of the bigger studies within the last years was published by Basch et al. 2017. The team conducted a randomised controlled trial with 766 metastatic cancer patients and showed that digital symptom monitoring during chemotherapy helps patients live longer (5.2 months longer median overall survival), improves quality of life (31% of patients), and reduces hospitalisation (4%) and ER visits (7%).

Trends driving change in Clinical- and real-world data Management.

Digital health technologies are expected to enable patients to receive rapid physician support for adverse events thus improving patient safety, decreasing attrition, and extending life. Supporting the collection of PROs and other data, they could also enable virtual trial formats, ease site work burden, and help end trials with poor outcomes earlier. 

They also support development of novel “functional” endpoints or digital biomarkers that measure clinical benefits. Increased focus on PROs will shed new light on patient outcomes (PROMs) and experience (PREMs) outside the clinical setting or at home, as well as track Performance Status, to inform ongoing clinical decisions, serve as secondary endpoints, influence labeling, and accelerate trial times. Real-world data is expected to speed trials by aiding in investigator/site selection, help optimize trial design including right-sizing trials for treatment effect, and enable new trial designs. Such designs include leveraging RWD as synthetic controls or comparators for new approvals and using RWE or registry data to conduct virtual trials post-approval for label expansions and provide supporting evidence of patient outcomes and overall survival in the real world. 

Predictive analytics and AI will identify new clinical hypotheses to test, reduce trial design risks, speed enrollment by identifying protocol-ready patients, and help narrow trial patient populations to pre-defined subgroups (i.e., precision medicine). It will also enable adaptive designs that lead to earlier approval with smaller patient samples, and increase the probability of success and approval. Availability of pools of pre-screened patients and direct-to-patient recruitment will facilitate trial recruitment and help sites/trials hit accrual targets. As providers/vendors conduct more diagnostic tests and record demographics and prior treatment, trials targeting defined patient subsets will find it easier to recruit. Where biomarker and genetic information is available, it may increase the number of patients available for early clinical studies. Although this is a significant part of the “future of oncology”, building and accessing such data may require significant investment. New, personalized, and intuitive healthcare ecosystems. Perhaps the most significant change could be the creation of intuitive and personalized ecosystems of care centered around patients and their families, into which their community of medical and social caregivers would be integrated. Such ecosystems would make possible the delivery of the right type and amount of care, in the right setting, at the right time. 

The digital feedbacks that can be designed from patient-collected data are set to disrupt healthcare like never before, allowing for earlier detection and prevention of diseases. Digital feedbacks could also provide longitudinal insights into diseases that progress over time for an individual patient, or a collective population. Novel insights can be gained into diseases that are not tracked well with current diagnostic tests, such as Alzheimer’s disease, dementia and depression. 

In addition, more engaged patients that are enabled to track their own health and set goals for lifestyle interventions can lead to better medication adherence and improved involvement in disease handling. Finally, the combination of digital feedbacks and traditional diagnostic results could improve the accuracy of diagnosis or even indicate when more accurate laboratory or monitoring biomarkes should be analyzed. For example, the availability of continuous data from a digital feedback can allow for better risk monitoring over time as opposed to a single snapshot of time provided by lab biomarkers. This could be linked to the assessment of digital patient feedbacks in clinical trials to replace current gold standards. 

Furthermore, the replacement of current technologies to monitor patient health could lead to a reduction of equipment for healthcare providers and improved patient satisfaction. One example of this is in the use of patient feedbacks to measure patient symptoms at home or in hospitals. With an internet connection and a smart phone, physicians are able to remotely monitor their patients. Thus, eliminating the need for bulky sensors, display equipment and an array of cables that prevent patients from being able to move comfortably. The built-in artificial intelligence (AI) enables intelligent processing of data to detect abnormalities, providing alerts to clinicians only when problems are detected and thereby reducing the burden to process the data