Jump to Content
Chirag Nagpal

Chirag Nagpal

I am a Research Scientist with the Context in AI Research (CAIR) Team within Google Responsible AI. My interests are in building machine learning algorithms, tools, pipelines and software that augment decision making by being robust, fair and having broad practical utility across all domains of interest to Alphabet.

I received my PhD from the School of Computer Science at Carnegie Mellon, where I gained extensive experience in probabilistic inference and numerical optimization for semi-parametric graphical models with applications in patient risk stratification and treatment benefit assessment.

My graduate research has seen application in numerous patient risk prediction problems across multiple areas of healthcare [1] [2], has spun open source software [3] [4], and has been taught at graduate courses in MIT and Harvard [5].
Authored Publications
Google Publications
Other Publications
Sort By
  • Title
  • Title, desc
  • Year
  • Year, desc
    Deep Cox Mixtures for Survival Regression
    Proceedings of the 6th Machine Learning for Healthcare Conference, PMLR (2021), pp. 674-708
    Preview abstract Survival analysis is a challenging variation of regression modeling because of the presence of censoring, where the outcome measurement is only partially known, due to, for example, loss to follow up. Such problems come up frequently in medical applications, making survival analysis a key endeavor in biostatistics and machine learning for healthcare, with Cox regression models being amongst the most commonly employed models. We describe a new approach for survival analysis regression models, based on learning mixtures of Cox regressions to model individual survival distributions. We propose an approximation to the Expectation Maximization algorithm for this model that does hard assignments to mixture groups to make optimization efficient. In each group assignment, we fit the hazard ratios within each group using deep neural networks, and the baseline hazard for each mixture component non-parametrically. We perform experiments on multiple real world datasets, and look at the mortality rates of patients across ethnicity and gender. We emphasize the importance of calibration in healthcare settings and demonstrate that our approach outperforms classical and modern survival analysis baselines, both in terms of discriminative performance and calibration, with large gains in performance on the minority demographics. View details
    No Results Found