Harvard Catalyst Profiles

Contact, publication, and social network information about Harvard faculty and fellows.

William LaCava, Ph.D.

Title
Institution
Department
Address
Profile Picture

Biography
University of Pennsylvania, Philadelphia, PA, USAPostdoc07/2020Biomedical Informatics
University of Massachusetts Amherst, Amherst, MAPhD09/2016Mechanical Engineering
Cornell University, Ithaca, NY, USAM.Eng.05/2010Mechanical and Aerospace Engineering
Cornell University, Ithaca, NY, USAB.S.05/2009Mechanical and Aerospace Engineering

Overview
Williams runs the Clarity- and Virtue-guided Algorithms Laboratory (Cava Lab) in the Computational Health Informatics Program at Boston Children's Hospital and Harvard Medical School. His research focuses on developing multi-objective learning methods and using them to explain the principles underlying biomedical processes. His lab uses these methods to learn predictive models from electronic health records (EHRs) that are both interpretable to clinicians and fair to the population on which they are deployed. His long-term goals are to positively impact human health by developing methods that are flexible enough to automate entire computational workflows underlying scientific discovery and medicine.

Mentoring
Available: 02/18/22, Expires: 03/01/24

The goal of this project is to develop and assess AI algorithms that predict the need for interventions during birth using electronic fetal monitoring (EFM) data. Electronic fetal monitoring (EFM) is currently used in 99% of all hospital births in the United States to monitor the fetal heart rate. Despite its ubiquity, substantial limitations persist in the efficacy, reliability, and accuracy of EFM in accomplishing its primary intended goal of preventing intrapartum fetal injury. One of the greatest challenges that obstetricians face is interpreting EFM; how to distinguish fetal distress that warrants an emergency cesarean delivery (CD) from a false alarm that can safely be ignored. After over 70 years of attempts to refine obstetricians interpretation of EFM, the results remain dismal. Up to 30% of CDs performed in the United States are thought to be done unnecessarily due to false-positive interpretations of fetal distress from EFM. Currently, EFM interpretation is dependent on clinicians visual inspection of the monitor strips as they print out at the patient bedside or scroll across a computer monitor. Doctors and nurses are taught to examine 4 particular features of the EFM and to categorize the tracing into one of three categories: normal (Category I), indeterminate (Category II), or abnormal (Category III). This method is deeply fraught. A large majority of intrapartum strips are categorized as indeterminate, which then leads to often unnecessary and potentially morbid interventions. Furthermore, interpretation of EFM is extremely subjective and highly vulnerable to biases; both inter-observer and intra-observer reliability of EFM interpretation are poor. Studies have shown that different doctors agree on interpretation of the same strip only 20-30% of the time, and doctors only agree with themselves approximately 70-80% of the time when asked to re-interpret a strip on a different day. The lack of consistency and accuracy in EFM interpretation has been proven to lead to unnecessary interventions without improved fetal outcomes, and this challenge plagues obstetrics. In recent years, machine learning approaches have shown great promise in facilitating data processing and pattern recognition in medicine, and we believe that the application of machine learning techniques to the problem of EFM interpretation has the potential to improve the predictive accuracy and reliability of intrapartum fetal monitoring. Student role: students will work closely with Dr. La Cava and other lab members to understand EFM data and develop deep learning models, trained on the time series data. Students will assess the efficacy of these methods in comparison to traditional approaches and other machine learning approaches. Prior skills: experience with data science tools and software development, especially Python, is preferred. Students will gain additional experience in code development using open source libraries and perform data visualization and statistical analysis.

Available: 12/07/22, Expires: 08/31/25

Our lab develops machine learning methods that optimize clinical risk prediction models to be fair to patients they are deployed on. In this project, the student will gain experience in this development process and assist in applying these methods to clinical applications. Application areas include: - emergency room admission risk prediction - fair resource allocation for hypertension management An ideal candidate will have some background or experience programming in Python, a solid grasp of statistics and familiarity machine learning. Tasks include data analysis and visualization, contributing to open source software, and running computational experiments on large sets of health records. Students will develop technical skills and a deeper understanding of clinical applications of AI.


Research
The research activities and funding listed below are automatically derived from NIH ExPORTER and other sources, which might result in incorrect or missing items. Faculty can login to make corrections and additions.
  1. R00LM012926 (LA CAVA, WILLIAM) Sep 1, 2021 - Aug 31, 2024
    NIH
    Multi-objective representation learning methods for interpetable predictions of patient outcomesusing electronic health records
    Role: Co-Investigator
  2. K99LM012926 (LA CAVA, WILLIAM) Jun 1, 2019 - May 31, 2021
    NIH
    Multi-objective representation learning methods for interpetable predictions of patient outcomesusing electronic health records
    Role: Co-Investigator

Featured Content

Bibliographic
Publications listed below are automatically derived from MEDLINE/PubMed and other sources, which might result in incorrect or missing publications. Faculty can login to make corrections and additions.
Newest   |   Oldest   |   Most Cited   |   Most Discussed   |   Timeline   |   Field Summary   |   Plain Text
PMC Citations indicate the number of times the publication was cited by articles in PubMed Central, and the Altmetric score represents citations in news articles and social media. (Note that publications are often cited in additional ways that are not shown here.) Fields are based on how the National Library of Medicine (NLM) classifies the publication's journal and might not represent the specific topic of the publication. Translation tags are based on the publication type and the MeSH terms NLM assigns to the publication. Some publications (especially newer ones and publications not in PubMed) might not yet be assigned Field or Translation tags.) Click a Field or Translation tag to filter the publications.
  1. La Cava W, Williams H, Fu W, Vitale S, Srivatsan D, Moore JH. Evaluating recommender systems for AI-driven biomedical informatics. Bioinformatics. 2021 04 19; 37(2):250-256. PMID: 32766825; PMCID: PMC8055228.
    Citations: 1     Fields:    Translation:Humans
  2. La Cava W, Moore JH. Learning feature spaces for regression with genetic programming. Genet Program Evolvable Mach. 2020 Sep; 21(3):433-467. PMID: 33343224; PMCID: PMC7748157.
    Citations:    
  3. Cava W, Bauer C, Moore JH, Pendergrass SA. Interpretation of machine learning predictions for patient outcomes in electronic health records. AMIA Annu Symp Proc. 2019; 2019:572-581. PMID: 32308851.
    Citations: 9     Fields:    Translation:Humans
  4. Urbanowicz RJ, Meeker M, La Cava W, Olson RS, Moore JH. Relief-based feature selection: Introduction and review. J Biomed Inform. 2018 09; 85:189-203. PMID: 30031057; PMCID: PMC6299836.
    Citations: 76     Fields:    Translation:Humans
  5. La Cava W, Helmuth T, Spector L, Moore JH. A Probabilistic and Multi-Objective Analysis of Lexicase Selection and e-Lexicase Selection. Evol Comput. 2019; 27(3):377-402. PMID: 29746157; PMCID: PMC9453780.
    Citations: 2     Fields:    Translation:Humans
  6. Olson RS, Cava W, Mustahsan Z, Varik A, Moore JH. Data-driven advice for applying machine learning to bioinformatics problems. Pac Symp Biocomput. 2018; 23:192-203. PMID: 29218881.
    Citations: 51     Fields:    Translation:Humans
  7. Olson RS, La Cava W, Orzechowski P, Urbanowicz RJ, Moore JH. PMLB: a large benchmark suite for machine learning evaluation and comparison. BioData Min. 2017; 10:36. PMID: 29238404; PMCID: PMC5725843.
    Citations: 31     
  8. LaCava W, Pantiskas C, Morse W. Monitoring pacemaker patients. J Clin Eng. 1994 Jan-Feb; 19(1):39-47. PMID: 10132707.
    Citations:    Translation:Humans
Local representatives can answer questions about the Profiles website or help with editing a profile or issues with profile data. For assistance with this profile: HMS/HSDM faculty should contact contactcatalyst.harvard.edu. For faculty or fellow appointment updates and changes, please ask your appointing department to contact HMS. For fellow personal and demographic information, contact HMS Human Resources at human_resourceshms.harvard.edu. For faculty personal and demographic information, contact HMS Office for Faculty Affairs at facappthms.harvard.edu.
LaCava's Networks
Click the
Explore
buttons for more information and interactive visualizations!
Concepts (26)
Explore
_
Similar People (60)
Explore
_
Same Department 
Explore
_
Funded by the NIH National Center for Advancing Translational Sciences through its Clinical and Translational Science Awards Program, grant number UL1TR002541.