|
Shane J. Sacco, PhDAssistant Professor
|
|||||
Education
Post-Graduate Training
| Degree | Institution | Major |
|---|---|---|
| BA | University of Connecticut | Psychological Sciences |
| PhD | University of Connecticut | Health Promotion Science |
Post-Graduate Training
| Training | Institution | Specialty |
|---|---|---|
| Postdoctoral | University of Connecticut | Statistics |
My current research aims to improve prediction of health outcomes using transfer-learning techniques, clinical decision-making pipelines, feature and outcome engineering, and uncertainty quantification. Over the last decade, I have been author and statistician on multiple grants and studies investigating mental and physical health including suicide, heart failure, dietary habits and obesity, meaning in life, veteran health, and other dimensions of biopsychosocial well-being. I have also focused on methodological advancements in modelling non-linear interactions.
Journal Articles
-
Screening and Risk Algorithms for Detecting Pediatric Suicide Risk in the Emergency Department.
JAMA network open 2025 Sep;8(9):e2533505
-
Using transfer learning to improve prediction of suicide risk in acute care hospitals.
Journal of the American Medical Informatics Association : JAMIA 2025 Jul;
-
Identifying patients at risk of suicide using data from health information exchanges.
BMC public health 2025 Apr;25(1):1582
-
Feasibility and importance of universal suicide screening in a pediatric emergency department.
PloS one 2025 Jan;20(6):e0321934
-
Accuracy and transportability of machine learning models for adolescent suicide prediction with longitudinal clinical records.
Translational psychiatry 2024 Jul;14(1):316
-
Target-based fusion using social determinants of health to enhance suicide prediction with electronic health records.
PloS one 2023 Jan;18(4):e0283595
| Title or Abstract | Type | Sponsor/Event | Date/Year | Location |
|---|---|---|---|---|
| Adjusting predictive model performance for real-world implementation: Are you being too optimistic or too pessimistic about your model built with electronic health records? | Talk | ICSA Applied Statistics Symposium | 2025 | |
| Should I go or should I stay now? Influence of Caregiver Presence on Suicide Risk Screening Outcomes | Poster | Pediatric Academic Society Annual Meeting | 2025 | |
| An active learning approach to help account for uncertainty of models deployed in healthcare | Talk | New England Statistical Society Conference | 2024 | |
| Improving Prediction of Adolescent Suicide Attempts with Electronic Health Records by Leveraging External Data Sources | Talk | American Statistical Association Mini Conference - CT | 2023 | |
| Tips and tricks to improve the speed of your prediction pipelines and other analyses | Talk | American Statistical Association Mini Conference – Statistical Computing | 2023 | |
| Improving prediction of suicide attempts in adolescents and young adults without mental health disorders | Talk | New England Statistical Society Conference | 2023 | |
| Target-based Fusion using Social Determinants of Health to Enhance Suicide Prediction with Electronic Health Records | Talk | New England Statistical Society Conference | 2022 | |
| Visualization Techniques to Help Determine Whether the Continuous Interaction Effect Assumption Is Met Within the Standard Interaction Model | Talk | American Statistical Association Conference on Statistical Practice | 2021 | |
| Developing a Comprehensive Effect Size for Moderation Tests from Simple Slopes Analysis | Poster | University of Connecticut CAHNR Graduate Student Forum | 2019 | |
| Extending Pharmacological Dose-Ranging Methods to Moderation Testing: Enhancing the Use of Likert Scales as Moderators | Poster | Deming Applied Statistics Conference | 2018 |