Current Projects
Predicting & Understanding Adverse Pregnancy Outcomes
Adverse pregnancy outcomes such as Preterm Birth and Preeclampsia, are major long-lasting public health problems being the leading causes of mortality and long-term disabilities among neonates and mothers. Our goal is to devise understandable machine learning models that combine clinical and genetic data for risk prediction, and assessing the effectiveness of the methods in clinical practice.
Predicting Necrotizing Entercolitis
Necrotizing enterocolitis (NEC) is a common, life-threatening intestinal disease that affects approximately 10% of premature infants during the first few weeks after birth. The project aims to deliver a set of MIL-based tools for prediction of NEC from metagenomic sequencing data combined with optional clinical or demographic metadata.
Project Page
Logic Learner
Logic Learner is an online learning tool that helps computer science, engineering, and mathematics students improve their fluency and problem solving process in writing proofs for propositional logic.
Project PageProximal Junctional Kyphosis
Proximal junctional kyphosis (PJK) is a postoperative complication that occurs relatively frequently in the adult spinal deformity (ASD) population. The project aims to use privileged information and knowledge distillation to improve predictive power in existing models.
Project Page
Infant Colic
Infant colic is defined as persistent inconsolable crying in healthy babies between 2 weeks and 4 months of age in which the baby appears to be in great discomfort and difficult to soothe. Our ongoing efforts and goals are to propose a refined diagnostic tool as well as study the underlying risk factors that lead to infant colic.
Project PageSymbolic Law Discovery
The project focuses on automatically discovering scientific laws from experimental data using encoders and deep network pipelines. Our approach holds a real promise to help speed up the rate of scientific discovery.
