Machine Learning and Statistics in Clinical Research Articles-Moving Past the False Dichotomy.
Finlayson SG, Beam AL, van Smeden M.
JAMA Pediatr. 2023 Mar 20. PMID: 36939696
Andrew Beam, PhD is an assistant professor in the Department of Epidemiology at the Harvard T.H. Chan School of Public Health, with secondary appointments in the Department of Biomedical Informatics at Harvard Medical School and the Department of Newborn Medicine at Brigham and Women's Hospital. His research develops and applies machine-learning methods to extract meaningful insights from clinical and biological datasets, and he is the recipient of a Pioneer Award from the Robert Wood Johnson Foundation for his work on medical artificial intelligence.
Previously he was a Senior Fellow at Flagship Pioneering and the founding head of machine learning at VL56, a Flagship-backed venture that seeks to use machine learning to improve our ability to engineer proteins.
He earned his PhD in 2014 from N.C. State University for work on Bayesian neural networks, and he holds degrees in computer science (BS), computer engineering (BS), electrical engineering (BS), and statistics (MS), also from N.C. State. He completed a postdoctoral fellowship in Biomedical Informatics at Harvard Medical School and then served as a junior faculty member.
Dr. Beam's group is principally concerned with improving, stream-lining, and automating decision-making in healthcare through the use of quantitative, data-driven methods. He does this through rigorous methodological research coupled with deep partnerships with physicians and other members of the healthcare workforce. As part of this vision, he works to see these ideas translated into decision-making tools that doctors can use to better care for their patients.
For more information, please see his group's website at beamlab.org
INSTRUMENTING THE NICU WITH MODERN PREDICTIVE TOOLS
We are developing deep learning models to equip neonatologists with modern predictive tools to help them better understand and care for their patients. Infants born prematurely (before 37 weeks of gestation) experience very high levels of morbidity and are among the most expensive patients in all of pediatrics. NICU infants generate a tremendous amount of high-signal, multimodal data as part of their clinical care, but this data is currently under-utilized to inform decision-making.
These modalities are ones where deep learning has had tremendous success to date (e.g. imaging, text), thus there is an opportunity to create highly accurate predictive models for proactive decision-making. Specifically, we are interested in developing models in the following areas:
Convolutional models for NICU imaging data including x-rays, ROP screens, and ultrasounds.
Recurrent and transformer models for admission, progress, and discharge notes.
Recurrent and transformer models of real-time monitoring data.
Longitudinal disease trajectories built using large administrative databases.
We are extremely interested in developing new techniques that combine two or more of the above modalities to enable "pan-diagnostic" capabilities for NICU patients. Beyond model development, we are very committed to translational research to better understand how these models can be implemented in clinical work flows in a natural, easy-to-use manner.
AUTOMATIC DIAGNOSIS AND MEDICAL REASONING WITH NLP/NLU
A large portion of the world's medical knowledge is in unstructured sources such as textbooks, websites, and biomedical journal articles. We are developing a large-scale natural language processing (NLP) and natural language understanding (NLU) system capable of extracting general medical and diagnostic principles from unstructured medical text. For this project, we have created a unique collection of biomedical texts containing of 4.3 million articles, 50,000 pages of reference material, 15,000 flash cards, dozens of medical text books, and 20,000 multiple choice medical questions.
Using this data, we are creating models that can perform a broad range of medical reasoning tasks such as providing a differential diagnosis on the basis of a short textual description and answering complex medical questions posed in natural language. This work starts with current state of the art NLP/NLU/QA models based on deep learning, but seeks to extend them with explicit forms of symbolic reasoning and other less traditional computational models that are not currently in vogue.
METHODS DEVELOPMENT TO MOVE BEYOND DEEP LEARNING
Deep learning has had tremendous success in medicine. However, despite these successes deep learning models are in fact brittle and there are classes of problems that are not solvable by deep learning, even in principle. Moreover, at least in its current framing, nearly all of modern machine learning techniques are designed to give predictions, but what doctors often want are decisions. This necessitates moving beyond simple correlation-based models towards ones with richer understanding of the world, and are capable of understanding the effects of interventions.
In collaboration with our colleagues in causal inference group at HSPH, we are exploring the interface of machine learning and causal inference methods. This is a new, but very active, area of research and we are excited what new questions can be answered as machine learning models are imbued with a causal understanding of the world.
Finlayson SG, Beam AL, van Smeden M.
JAMA Pediatr. 2023 Mar 20. PMID: 36939696
Kompa B, Hakim JB, Palepu A, Kompa KG, Smith M, Bain PA, Woloszynek S, Painter JL, Bate A, Beam AL.
Drug Saf. 2023 Feb 24. PMID: 36826708
Levine DM, Tuwani R, Kompa B, Varma A, Finlayson SG, Mehrotra A, Beam A.
medRxiv. 2023 Feb 01. PMID: 36778449
Sharma P, Beam K, Levy P, Beam AL.
J Perinatol. 2023 02. 43(2):257-258. PMID: 36646822
Natarajan A, Lam G, Liu J, Beam AL, Beam KS, Levin JC.
J Perinatol. 2023 02. 43(2):209-214. PMID: 36611107
Levin JC, Beam AL, Fox KP, Hayden LP.
Am J Perinatol. 2022 Aug 25. PMID: 35523410
Bellamy D, Hernán MA, Beam A.
Eur J Epidemiol. 2022 Jun. 37(6):563-568. PMID: 35792990
Green AG, Yoon CH, Chen ML, Ektefaie Y, Fina M, Freschi L, Gröschel MI, Kohane I, Beam A, Farhat M.
Nat Commun. 2022 07 02. 13(1):3817. PMID: 35780211
Hart JM, Hakim JB, Wylie BJ, Beam AL.
J Perinat Med. 2022 Nov 25. 50(9):1203-1209. PMID: 35654442
Kompa B, Hakim JB, Palepu A, Kompa KG, Smith M, Bain PA, Woloszynek S, Painter JL, Bate A, Beam AL.
Drug Saf. 2022 05. 45(5):477-491. PMID: 35579812
Andrew Beam, deputy editor of a new journal on AI and co-host of a podcast on the topic, discusses both the potential and challenges of the powerful tool.
A new artificial intelligence chatbot has the potential to transform the future of medical diagnosis, according to a February 13 op-ed in STAT co-authored by Andrew Beam, an assistant professor of epidemiology at Harvard Chan School.
As algorithms analyze mammograms and smartphones capture lived experiences, researchers are debating the use of ai in public health.