Marcos Matabuena
Postdoctoral researcher in the department of biostatistics at Harvard University. Onnela Lab mmatabuena@hsph.harvard.edu
Biostatistics, machine learning, and precision medicine with applications in physical activity, diabetes and wearable technology
About me
I develop advanced statistical and machine learning methods for digital and precision medicine, primarily focusing on analyzing data from wearable devices in diabetes and physical activity.
I develop advanced statistical and machine learning methods for digital and precision medicine, primarily focusing on analyzing data from wearable devices in diabetes and physical activity.
One of my significant contributions within the field of diabetes is the introduction of "glucodensity," a functional representation of time series data. Glucodensity representation improves existing clinical markers used for diabetes diagnosis and monitoring by capturing more information about individual glucose homeostasis. Additionally, I have made advancements in statistical methodology, including the creation of the biclustering algorithm for complex data, which has proven instrumental in analyzing diverse datasets. Furthermore, I have developed the first algorithm for quantifying uncertainty in metric spaces.
One of my significant contributions within the field of diabetes is the introduction of "glucodensity," a functional representation of time series data. Glucodensity representation improves existing clinical markers used for diabetes diagnosis and monitoring by capturing more information about individual glucose homeostasis. Additionally, I have made advancements in statistical methodology, including the creation of the biclustering algorithm for complex data, which has proven instrumental in analyzing diverse datasets. Furthermore, I have developed the first algorithm for quantifying uncertainty in metric spaces.
As a researcher, I pride myself on my creativity and collaborative nature. I strive to maintain a comprehensive perspective on statistical, mathematical, and biomedical research, recognizing the interconnectedness of these domains. My ultimate goal is to develop robust data analysis tools that will shape the future of medicine. Currently, my research encompasses various areas, including uncertainty quantification, causal inference in digital medicine, and survival analysis models that leverage the power of neural networks. These specific research domains have been motivated by critical biological challenges and the importance of translating these findings into clinical applications in biomedicine.
As a researcher, I pride myself on my creativity and collaborative nature. I strive to maintain a comprehensive perspective on statistical, mathematical, and biomedical research, recognizing the interconnectedness of these domains. My ultimate goal is to develop robust data analysis tools that will shape the future of medicine. Currently, my research encompasses various areas, including uncertainty quantification, causal inference in digital medicine, and survival analysis models that leverage the power of neural networks. These specific research domains have been motivated by critical biological challenges and the importance of translating these findings into clinical applications in biomedicine.
Selected scientific results
Selected scientific results
Distributional data analysis of accelerometer data from the NHANES database using nonparametric survey regression models
Research in pictures
Research in pictures
Transition from prediabetes to diabetes with glucodensities
Transition from prediabetes to diabetes with glucodensities
Uncertainity quantification in metric spaces
Uncertainity quantification in metric spaces