Seed Report: Predictive Models of Fertility

This CISE Seed Grant funded doctoral student Tinting Xu (ECE, SE) to work under the supervision of Director of CISE, Ioannis Ch. Paschalidis (ECE, BME, SE), and Assistant Professor Shruthi Mahalingaiah (Obstetrics & Gynecology) in developing data-driven, accurate, and personalized fertility prediction models.

These models can be used: (i) to help women and couples make timely and cost-effective family planning decisions; (ii) for early detection of reduced fertility, ideally before ART becomes ineffective; and (iii) for early detection of specific pathologies that lead to reduced fertility.

The funding supported the following activities:

Extramural funding received: NSF grant ($1.2M for 3 years), entitled “SCH: INT: Distributed Analytics for Enhancing Fertility in Families”

Lectures/publications produced:

  • Six invited lectures in various universities.
  • “Predicting Diabetes-related Hospitalizations based on Electronic Health Records”(with Theodora S. Brisimi, Tingting Xu, Taiyao Wang, and Wuyang Dai), Statistical Methods in Medical Research, in print, doi: doi.org/10.1177/0962280218810911.
  • “Detection of Unwarranted CT Radiation Exposure from Patient and Imaging Protocol Meta-Data Using Regularized Regression” (with Ruidi Chen, Vladimir Valtchinov, Jenifer Siegelman, Hiroto Hatabu), European Journal of Radiology Open, Vol. 6, pages 206-211, 2019, doi: https://doi.org/10.1016/j.ejro.2019.04.007.
  • “Designing metabolic division of labor in microbial communities” (with Meghan Thommes, Taiyao Wang, Qi Zhao, and Daniel Segre), mSystems, Vol. 4, Issue 2, March-April 2019, doi: doi.org/10.1128/mSystems.00263-18.
  • “Learning Policies for Markov Decision Processes from Data” (with Manjesh K. Hanawaly, Hao Liu, Henghui Zhu), IEEE Transactions on Automatic Control, Vol. 64, Issue 6, June 2019, pages 2298-2309, doi: doi.org/10.1109/TAC.2018.2866455.
  • “A Robust Learning Approach for Regression Models Based on Distributionally Robust Optimization” (with Ruidi Chen), Journal on Machine Learning Research, Vol. 19, 2018, No. 13, pages 1 -48, http://jmlr.org/papers/v19/17-295.html.
  • “Neural Circuits for Learning Context-Dependent Associations of Stimuli” (with Henghui Zhu and Michael Hasselmo), Neural Networks (Special Issue on Deep Reinforcement Learning in Neural Networks), Ron Sun, David Silver, Gerald Tesauro, Guang-Bin Huang, Eds., Vol. 107, November, 2018, pages 48-60 doi.org/10.1016/j.neunet.2018.07.018.
  • “Protein docking refinement by convex underestimation in the low-dimensional subspace of encounter complexes” (with Shahrooz Zarba an, Mohammad Moghadasi, Athar Roshandelpoor, Feng Nan, Keyong Li, Pirooz Vakili, Sandor Vajda, Dima Kozakov), Scientific reports, 2018, 8:5896, doi: dx.doi.org/10.1038/s41598-018-23982-3.
  • “Learning models for writing better doctor prescriptions” (with Tingting Xu), European Control Conference, June 25-28, 2019, Napoli, Italy.
  • “Prescriptive Cluster-Dependent Support Vector Machines with an Application to Reducing Hospital Readmissions” (with Taiyao Wang), European Control Conference, June 25-28, 2019, Napoli, Italy.
  • “Learning Parameterized Prescription Policies and Disease Progression Dynamics using Markov Decision Processes” (with Henghui Zhu and Tingting Xu), American Control Conference, July 10-12, 2019, Philadelphia, Pennsylvania.
  • “A Hebbian learning algorithm for training a neural circuit to perform context-dependent associations of stimuli” (with Henghui Zhu and Michael Hasselmo), American Control Conference, July 10-12, 2019, Philadelphia, Pennsylvania.
  • “Clinical Concept Extraction with Contextual Word Embedding”, (with Henghui Zhu and Amir Tahmasebi), NIPS Machine Learning for Health Workshop, December 8, 2018, Montreal, Canada.
  • “Learning Optimal Personalized Treatment Rules Using Robust Regression Informed K-NN,” (with Ruidi Chen), NIPS Machine Learning for Health Workshop, December 8, 2018, Montreal, Canada.
  • “Context-Driven Concept Annotation in Radiology Reports: Anatomical Phrase Labeling,” (with Henghui Zhu and Amir Tahmasebi), AMIA 2019 Informatics Summit, March 25-28, 2019, San Francisco, California.
  • “Context-based bidirectional-LSTM model for sequence labeling in clinical reports” (with Henghui Zhu and Amir Tahmasebi), SPIE Medical Imaging Symposium, February 6-21, 2019, San Diego, California, doi: https://doi.org/10.1117/12.2512103.
  • “A Distributionally Robust Optimization Approach for Outlier Detection” (with R. Chen), Proceedings of the 57th IEEE Conference on Decision and Control, pages 352-357, December 17-19, 2018, Miami, Florida, doi: dx.doi.org/10.1109/CDC.2018.8619435.
  • “From Data to Models and Proposed Solutions”, Invited Talk, Workshop on Control for Networked Transportation Systems (CNTS), July 9, 2019, Philadelphia, Pennsylvania.
  • “Distributionally Robust Learning with Applications to Health Analytics,” Invited Talk, 2nd Information Modeling & Control of Complex Systems (IMaCCS) Workshop, June 3-4, 2019, Ohio State University, Columbus, Ohio.
  • “Using Machine Learning to Build a Highly Specific Prediction Model of Conception” (with Tingting Xu and Shruthi Mahalingaiah), New England Fertility Society Annual Meeting, May 3-4, 2019, Omni Mt. Washington, Bretton Woods, New Hampshire.
  • “Automatic Extraction of Incidental Pulmonary Nodule Findings in Radiology Reports” (with Henghui Zhu, Amir M. Tahmasebi), Annual Meeting of the Society for Imaging Informatics in Medicine (SIIM), June 26-June 28, 2019, Denver, Colorado.