Urteaga Named 2021 STAT Wunderkind

Dec 10 2021

Dr. Iñigo Urteaga, Associate Research Scientist in the APAM Department, has been named a 2021 STAT Wunderkind in recognition of his work on the development of statistical modeling for mobile health data.

STAT is a leading publication in medical news, and its annual Wunderkind list honors early career scientists who are doing groundbreaking work in their field. This award recognizes the contributions of Dr. Urteaga as part of the multi-disciplinary research carried out along with Prof. Chris Wiggins (APAM) and Prof. Noémie Elhadad (DBMI) on the development of statistical modeling and data science solutions for mobile health data.

The increasing availability of personal mobile health data opens up new opportunities for health insights, increased self-awareness, and informed health and wellness decisions. However, despite the ongoing research in machine learning for healthcare in general, there remain important knowledge gaps on effective statistical techniques that leverage self-tracked mobile data to answer questions related to personalized health.

Dr. Urteaga's most recent applied mathematics work has focused on the realm of self-tracked health data, where physiological and behavioral patterns are entangled. His research encompasses the theoretical understanding, development and implementation of computational statistics and data science techniques for complex healthcare settings, by extending statistical models and inference methods to provide meaningful and robust insights from heterogeneous, dynamic, noisy and incomplete data. Over the last few years, he has contributed to the field of digital phenotyping and statistical predictive modeling for mobile health data (see references below).

His research in statistical modeling for healthcare demands not only methodological innovations (that accurately disentangle information from spurious signals) but novel interdisciplinary collaborations (e.g., with mobile health data providers, clinicians and bio-informaticians).

Dr. Iñigo Urteaga, Associate Research Scientist

Dr. Iñigo Urteaga, Associate Research Scientist

[1] A generative modeling approach to calibrated predictions: a use case on menstrual cycle length prediction. I Urteaga, K Li, A Shea, VJ Vitzthum, CH Wiggins, N Elhadad. Machine Learning for Healthcare Conference, 535-566. 2021 (https://proceedings.mlr.press/v149/urteaga21a.html)

[2] A predictive model for next cycle start date that accounts for adherence in menstrual self-tracking. K Li, I Urteaga, A Shea, VJ Vitzthum, CH Wiggins, N Elhadad. Journal of the American Medical Informatics Association. 2021 (https://academic.oup.com/jamia/advance-article/doi/10.1093/jamia/ocab182/6371799)

[3] Characterizing physiological and symptomatic variation in menstrual cycles using self-tracked mobile-health data. K Li, I Urteaga, CH Wiggins, A Druet, A Shea, VJ Vitzthum, N Elhadad. NPJ digital medicine 3 (1), 1-13. 2020 (https://www.nature.com/articles/s41746-020-0269-8)

[4] Learning endometriosis phenotypes from patient-generated data. I Urteaga, M McKillop, N Elhadad. NPJ digital medicine 3 (1), 1-14. 2020 (https://www.nature.com/articles/s41746-020-0292-9)

 

 

Stay up-to-date with the Columbia Engineering newsletter

* indicates required