I research the use of machine learning to facilitate interpretable causal inference, with a particular focus on medical applications. My recent work includes estimating dynamic treatment regimes for ICU patients, developing an interpretable method for observational causal inference, and creating a variant of multilabel learning to improve the prediction of rare clinical events. My collaborations span statistics, computer science, medicine, and chemistry.

Papers

Quinn Lanners*, Qin Weng*, Marie-Louise Meng, and Matthew M. Engelhard. Common Event Tethering to Improve Prediction of Rare Clinical Events. In Conference on Uncertainty in Artificial Intelligence (UAI), 2024. [Spotlight] Link

Harsh Parikh*, Quinn Lanners*, Zade Akras, Sahar F. Zafar, M. Brandon Westover, Cynthia Rudin, and Alexander Volfovsky. Safe and interpretable estimation of optimal treatment regimes. In International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR 238:2134-2142, 2024. Link

Quinn Lanners, Harsh Parikh, Alexander Volfovsky, Cynthia Rudin, and David Page. Variable importance matching for causal inference. In Conference on Uncertainty in Artificial Intelligence (UAI), PMLR 216:1174–1184, 2023. Link

Samantha M McDonald, Emily K Augustine, Quinn Lanners, Cynthia Rudin, L Catherine Brinson, and Matthew L Becker. Applied machine learning as a driver for polymeric biomaterials design. Nature Communications, 14(1):4838, 2023. Link

Marie-Louise Meng, Yuqi Li, Matthew Fuller, Quinn Lanners, Ashraf S Habib, Jerome J Federspiel, Johanna Quist-Nelson, Svati H Shah, Michael Pencina, Kim Boggess, Vijay Krishnamoorthy, and Matthew Engelhard. Development and Validation of a Predictive Model for Maternal Cardiovascular Morbidity Events in Patients With Hypertensive Disorders of Pregnancy. Anesthesia & Analgesia, 2022. Link

Quinn Lanners and Thomas Laurent. Neural machine translation. Honors thesis, Loyola Marymount University, 2019. Link


Short Papers

Mohamed A. Radwan, Himaghna Bhattacharjee, Quinn Lanners, Jiasheng Zhang, Serkan Karakulak, Houssam Nassif, and Murat Ali Bayir. Counterfactual evaluation of ads ranking models through domain adaptation. Accepted to the Causality, Counterfactuals & Sequential Decision Making workshop at RecSys, 2024. Link


Conference Presentations

Quinn Lanners, Harsh Parikh, Cynthia Rudin, Alexander Volfovsky, and Caleb Miles. Combining rct and observational study data in the presence of unmeasured confounding. Presented at the Joint Statistical Meetings in Portland, OR, USA, 2024.

Quinn Lanners, Harsh Parikh, Alexander Volfovsky, Cynthia Rudin, and David Page. Flexible almost-exact matching for trustworthy causal inference. Presented at the Joint Statistical Meetings in Portland, OR, USA, 2024.

Quinn Lanners*, Qin Weng*, Marie-Louise Meng, and Matthew M Engelhard. Common event tethering to improve prediction of rare clinical events. Spotlight presentation at The 40th Conference on Uncertainty in Artificial Intelligence in Barcelona, Spain, 2024.

Harsh Parikh*, Quinn Lanners*, Zade Akras, Sahar F. Zafar, M. Brandon Westover, Cynthia Rudin, and Alexander Volfovsky. Estimating trustworthy and safe optimal treatment regimes for treating seizures in critically ill icu patients. Presented at Duke Health Data Science Showcase in Durham, NC, USA, 2023.

Quinn Lanners, Harsh Parikh, Alexander Volfovsky, Cynthia Rudin, and David Page. Variable importance matching for causal inference. Presented at INFORMS Annual Meeting in Phoenix, AZ, USA, 2023.

Quinn Lanners, Harsh Parikh, Alexander Volfovsky, Cynthia Rudin, and David Page. Matching using feature importance: An auditable approach to causal inference. Presented at the 9th International Conference of Computational Social Science in Copenhagen, Denmark, 2023.

Quinn Lanners Neural machine translation. Presented at Optum/UHG/UHC Analytics Conference in Eden Prairie, MN, USA, 2019.

Quinn Lanners and Lambert Doezema. The current state of atmospheric gas concentrations in california - as observed through data collected through nasa’s student airborne research program. Presented at the Southern California Conferences for Undergraduate Research at California State Polytechnic University, Pomona, 2017.


Articles

Neural Machine Translation: A guide to Neural Machine Translation using an Encoder Decoder structure with attention. Link

Deploying a Scikit-Learn Model on AWS Using SKLearn Estimators, Local Jupyter Notebooks, and the Terminal. Link

Choosing a Scikit-learn Linear Regression Algorithm. Link

Why You Should Know How to Deploy Your Models in the Cloud. Link

*co-first author