TY - JOUR
T1 - Deep digital phenotyping in type 1 diabetes
T2 - The reinvention of epidemiological research
AU - Fagherazzi, Guy
N1 - Funding Information:
le projet World Diabetes Distress Study (WDDS) est soutenu par la Fondation MSDAvenir, le Luxembourg Institute of Health, et la Soci?t? Francophone du Diab?te (SFD). Le projet VOCADIAB est ?galement soutenu par le Luxembourg Institute of Health et la Soci?t? Francophone du Diab?te. L??tude SFDT1 est promue par la Fondation Francophone pour la Recherche sur le Diab?te (FFRD) et par la Soci?t? Francophone du Diab?te (SFD), et est rendue possible gr?ce au partenariat avec Lilly, Abbott, Air Liquide, et gr?ce aux dons de Novo Nordisk, Sanofi, Insulet.
Publisher Copyright:
© 2021 Elsevier Masson SAS
PY - 2021/6
Y1 - 2021/6
N2 - Digital technology offers new opportunities to better characterize, the reality of daily life of people with type 1 diabetes. The “digitosome”, the digital data generated online by individuals during their lifetime, is an unprecedented source of information to be analyzed using artificial intelligence methods (digital phenotyping), to be combined with other clinical and omics data (deep phenotyping). Thus, this concept of deep digital phenotyping will make it possible to obtain more holistic characterizations of people with diabetes and then to identify, in large cohorts, their digital twin and offer them precision health programs, personalized diabetes and therapeutic management. These concepts, as well as the vigilance required to guard against possible drifts related to the misuse of data and to artificial intelligence are discussed in this article based on current research developments.
AB - Digital technology offers new opportunities to better characterize, the reality of daily life of people with type 1 diabetes. The “digitosome”, the digital data generated online by individuals during their lifetime, is an unprecedented source of information to be analyzed using artificial intelligence methods (digital phenotyping), to be combined with other clinical and omics data (deep phenotyping). Thus, this concept of deep digital phenotyping will make it possible to obtain more holistic characterizations of people with diabetes and then to identify, in large cohorts, their digital twin and offer them precision health programs, personalized diabetes and therapeutic management. These concepts, as well as the vigilance required to guard against possible drifts related to the misuse of data and to artificial intelligence are discussed in this article based on current research developments.
KW - Artificial intelligence
KW - Cohort
KW - Data
KW - Digital twin
KW - Epidemiology
UR - http://www.scopus.com/inward/record.url?scp=85105063566&partnerID=8YFLogxK
U2 - 10.1016/j.mmm.2021.04.005
DO - 10.1016/j.mmm.2021.04.005
M3 - Short survey
AN - SCOPUS:85105063566
SN - 1957-2557
VL - 15
SP - 375
EP - 379
JO - Medecine des Maladies Metaboliques
JF - Medecine des Maladies Metaboliques
IS - 4
ER -