TY - JOUR
T1 - From hype to reality
T2 - Data science enabling personalized medicine
AU - Fröhlich, Holger
AU - Balling, Rudi
AU - Beerenwinkel, Niko
AU - Kohlbacher, Oliver
AU - Kumar, Santosh
AU - Lengauer, Thomas
AU - Maathuis, Marloes H.
AU - Moreau, Yves
AU - Murphy, Susan A.
AU - Przytycka, Teresa M.
AU - Rebhan, Michael
AU - Röst, Hannes
AU - Schuppert, Andreas
AU - Schwab, Matthias
AU - Spang, Rainer
AU - Stekhoven, Daniel
AU - Sun, Jimeng
AU - Weber, Andreas
AU - Ziemek, Daniel
AU - Zupan, Blaz
N1 - We thank Colin Birkenbihl for providing Fig. 5. CB has been partially supported by the IMI project AETIONOMY (https://www.aetionomy.eu/en/vision.html) within the 7th Framework Programme of the European Union.
This work is an outcome of Dagstuhl seminar 17472 “Addressing the Computational Challenges of Personalized Medicine” (http://www.dagstuhl.de/ de/programm/kalender/semhp/?semnr=17472), which was organized by authors HF, NB, and SM. We thank Schloss Dagstuhl for the support of our meeting. HF was partially supported by the IMI project AETIONOMY (https:// www.aetionomy.eu/en/vision.html) within the 7th Framework Programme of the European Union. TMP was supported in part by the Intramural Research Program of the National Institutes of Health, National Library of Medicine. MS was partially supported by the Robert-Bosch Stiftung, Stuttgart, Germany, and the European Commission Horizon 2020 UPGx grant (668353). The funders had no influence on the content of this manuscript.
PY - 2018/8/27
Y1 - 2018/8/27
N2 - Background: Personalized, precision, P4, or stratified medicine is understood as a medical approach in which patients are stratified based on their disease subtype, risk, prognosis, or treatment response using specialized diagnostic tests. The key idea is to base medical decisions on individual patient characteristics, including molecular and behavioral biomarkers, rather than on population averages. Personalized medicine is deeply connected to and dependent on data science, specifically machine learning (often named Artificial Intelligence in the mainstream media). While during recent years there has been a lot of enthusiasm about the potential of 'big data' and machine learning-based solutions, there exist only few examples that impact current clinical practice. The lack of impact on clinical practice can largely be attributed to insufficient performance of predictive models, difficulties to interpret complex model predictions, and lack of validation via prospective clinical trials that demonstrate a clear benefit compared to the standard of care. In this paper, we review the potential of state-of-the-art data science approaches for personalized medicine, discuss open challenges, and highlight directions that may help to overcome them in the future. Conclusions: There is a need for an interdisciplinary effort, including data scientists, physicians, patient advocates, regulatory agencies, and health insurance organizations. Partially unrealistic expectations and concerns about data science-based solutions need to be better managed. In parallel, computational methods must advance more to provide direct benefit to clinical practice.
AB - Background: Personalized, precision, P4, or stratified medicine is understood as a medical approach in which patients are stratified based on their disease subtype, risk, prognosis, or treatment response using specialized diagnostic tests. The key idea is to base medical decisions on individual patient characteristics, including molecular and behavioral biomarkers, rather than on population averages. Personalized medicine is deeply connected to and dependent on data science, specifically machine learning (often named Artificial Intelligence in the mainstream media). While during recent years there has been a lot of enthusiasm about the potential of 'big data' and machine learning-based solutions, there exist only few examples that impact current clinical practice. The lack of impact on clinical practice can largely be attributed to insufficient performance of predictive models, difficulties to interpret complex model predictions, and lack of validation via prospective clinical trials that demonstrate a clear benefit compared to the standard of care. In this paper, we review the potential of state-of-the-art data science approaches for personalized medicine, discuss open challenges, and highlight directions that may help to overcome them in the future. Conclusions: There is a need for an interdisciplinary effort, including data scientists, physicians, patient advocates, regulatory agencies, and health insurance organizations. Partially unrealistic expectations and concerns about data science-based solutions need to be better managed. In parallel, computational methods must advance more to provide direct benefit to clinical practice.
KW - Artificial intelligence
KW - Big data
KW - Biomarkers
KW - Machine learning
KW - P4 medicine
KW - Personalized medicine
KW - Precision medicine
KW - Stratified medicine
UR - http://www.scopus.com/inward/record.url?scp=85052330915&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85052330915&partnerID=8YFLogxK
U2 - 10.1186/s12916-018-1122-7
DO - 10.1186/s12916-018-1122-7
M3 - Article
C2 - 30145981
AN - SCOPUS:85052330915
SN - 1741-7015
VL - 16
JO - BMC Medicine
JF - BMC Medicine
IS - 1
M1 - 150
ER -