Personalized Clinical Phenotyping through Systems Medicine and Artificial Intelligence

Abstract

Personalized Medicine (PM) has shifted the traditional top-down approach to medicine based on the identification of single etiological factors to explain diseases, which was not suitable for explaining complex conditions. The concept of PM assumes several interpretations in the literature, with particular regards to Genetic and Genomic Medicine. Despite the fact that some disease-modifying genes affect disease expression and progression, many complex conditions cannot be understood through only this lens, especially when other lifestyle factors can play a crucial role (such as the environment, emotions, nutrition, etc.). Personalizing clinical phenotyping becomes a challenge when different pathophysiological mechanisms underlie the same manifestation. Brain disorders, cardiovascular and gastroenterological diseases can be paradigmatic examples. Experiences on the field of Fondazione Policlinico Gemelli in Rome (a research hospital recognized by the Italian Ministry of Health as national leader in “Personalized Medicine” and “Innovative Biomedical Technologies”) could help understanding which techniques and tools are the most performing to develop potential clinical phenotypes personalization. The connection between practical experiences and scientific literature highlights how this potential can be reached towards Systems Medicine using Artificial Intelligence tools.

Radiomic models for lymph node metastasis prediction in cervical cancer: can we think beyond sentinel lymph node?

“…Nevertheless, despite a sound methodology with several tested models merging the information coming from logistic regressions and more advanced machine learning solutions, the Authors do not clarify the possible biological meaning of the involved radiomics features. This confirms the lack of biological correlations as one of the most significant weakness of current radiomics investigations, strongly limiting the translational and personalized medicine applications of this recent and promising analysis technique, especially when not coupled with clinical data, as correctly argued by the Authors [ 27 , 28 ].…”

Challenges of Prevention for a Sustainable Personalized Medicine

“…Because rehabilitation requires an intimate understanding of how severe brain injuries impact disability, impairments, and QoL, PM represents a great opportunity for brain injury survivors to improve recovery [43]. In the perspective, we can consider the impact of omic sciences to address the most appropriate rehabilitation treatment on the basis of patients' needs, characteristics and life experience [30,[44][45][46].…”

“…Towards the systematic collection and study of clinical phenotypes and biomarkers, Rehabilomics can help in identifying relevant molecular or physiological fingerprints for anticipating long term outcome that can be linked to plasticity, treatment response, and natural recovery [43,[52][53][54], especially in emergency situation [55]. Rehabilomics encompasses rehabilitation research that uses biomarkers in its design.…”

Building an Artificial Intelligence Laboratory Based on Real World Data: The Experience of Gemelli Generator

“…This is compounded with the need to implement and integrate innovative approaches to provide clinicians and researchers with Real World information to gain a more complete picture and understanding of the patient by capturing their unique characteristics (Ahmed et al, 2020;Cesario et al, 2021b). To fully implement and benefit from this innovative approach, integration of mixed and heterogeneous data from several domains and contexts should be addressed, including personal factors, such as education, lifestyle, physical functions, environmental and social elements, and individual preferences (Cesario et al, 2021c). Thus, in this perspective, electronic health records (EHR) need to be augmented by assorted data sources, among which tools like questionnaires, wearable devices and mobile applications, which collect Patient Reported Outcomes (PROs), and Patient Reported Experiences (PREs), innovative and promising RWD sources.…”