. I am a MD-PhD Student at Harvard-MIT working with Dr. Isaac Kohane. My research interests center on the intersection of machine learning and healthcare. My current projects focus on exploring applications of deep learning to medical images, medical text, and various 'omics.
In addition to my research, I am involved in Hydrocephalus by way of Team Hydro
, an organization that my family and I started to raise money/awareness for the condition in honor of my sister, Kate. I also work part-time as a clinical data scientist at nference.ai
For a more formal account of my work, see my Curriculum Vitae
or Google Scholar
PhD Candidate, Systems Biology
Advisor: Isaac Kohane
Harvard Medical School, MIT
MD-PhD Program, MSTP Fellowship
MS, Biomedical Informatics
Research Mentor: Nigam Shah
BA, Human Biology - Biocomputation
Research Mentor: Daniel Rubin
Adversarial Attacks Against Medical Deep Learning Systems
. Abstract: The discovery of adversarial examples has raised concerns about the practical deployment of deep learning systems. In this paper, we argue that the field of medicine may be uniquely susceptible to adversarial attacks, both in terms of monetary incentives and technical vulnerability. To this end, we outline the healthcare economy and the incentives it creates for fraud, we extend adversarial attacks to three popular medical imaging tasks, and we provide concrete examples of how and why such attacks could be realistically carried out. For each of our representative medical deep learning classifiers, both white and black box attacks were both effective and human-imperceptible...
Samuel Finlayson, Isaac Kohane, Andrew Beam
Building the Graph of Medicine from Millions of Clinical Narratives
. Abstract: Electronic health records (EHR) represent a rich and relatively untapped resource for characterizing the true nature of clinical practice and for quantifying the degree of inter-relatedness of medical entities such as drugs, diseases, procedures and devices. We provide a unique set of co-occurrence matrices, quantifying the pairwise mentions of 3 million terms mapped onto 1 million clinical concepts, calculated from the raw text of 20 million clinical notes spanning 19 years of data...
Samuel Finlayson, Paea LePendu, Nigam Shah
Toward rapid learning in cancer treatment selection: An analytical engine for practice-based clinical data
Journal of Biomedical Informatics
. Abstract: Wide-scale adoption of electronic medical records (EMRs) has created an unprecedented opportunity for the implementation of Rapid Learning Systems (RLSs) that leverage primary clinical data for real-time decision support. In cancer, where large variations among patient features leave gaps in traditional forms of medical evidence, the potential impact of a RLS is particularly promising. We developed the Melanoma Rapid Learning Utility (MRLU), a component of the RLS, providing an analytical engine and user interface that enables physicians to gain clinical insights by rapidly identifying and analyzing cohorts of patients similar to their own....
Samuel Finlayson, Mia Levy, Sunil Reddy, Daniel Rubin
Predictability and persistence of prebiotic dietary supplementation in a healthy human cohort
. Abstract: Dietary interventions to manipulate the human gut microbiome for improved health have received increasing attention. However, their design has been limited by a lack of understanding of the quantitative impact of diet on a host’s microbiota. We present a highly controlled diet perturbation experiment in a healthy, human cohort in which individual micronutrients are spiked in against a standardized background. We identify strong and predictable responses of specific microbes across participants consuming ...
Thomas Gurry, HST Microbiome Consortium, ... Eric Alm
Potential Adverse Effects of Broad-Spectrum Antimicrobial Exposure in the Intensive Care Unit
Open Forum Infectious Diseases
. Abstract: The potential adverse effects of empiric broad-spectrum antimicrobial use among patients with suspected but subsequently excluded infection have not been fully characterized. We sought novel methods to quantify the risk of adverse effects of broad-spectrum antimicrobial exposure among patients admitted to an intensive care unit (ICU)...
Jenna Wiens, Graham Snyder, Samuel Finlayson, Monica Majoney, Leo Celi
Detecting Unplanned Care From Clinician Notes in Electronic Health Records
Journal of Oncology Practice
. Abstract: Purpose: Reduction in unplanned episodes of care, such as emergency department visits and unplanned hospitalizations, are important quality outcome measures. However, many events are only documented in free-text clinician notes and are labor intensive to detect by manual medical record review. Methods: We studied 308,096 free-text machine-readable documents linked to individual entries in our electronic health records,...
Suzanne Tamang, Manali Patel,... Samuel Finlayson, Yohan Vetteth, Nigam Shah