Avi Ma’ayan, PhD, Director of the Mount Sinai Center for Bioinformatics at the Icahn School of Medicine at Mount Sinai

Birth defects can be linked to many factors—genetic, environmental, even pure chance. Characterizing the links of any factor to congenital abnormalities is a daunting task, given the vastness of the problem.

In the face of this challenge, a team of researchers at the Icahn School of Medicine at Mount Sinai tapped artificial intelligence (AI) methods to shed light on associations between existing medications and their potential to induce specific birth abnormalities.

“We wanted to improve our understanding of reproductive health and fetal development, and importantly, warn about the potential of new drugs to cause birth defects before these drugs are widely marketed and distributed,” says Avi Ma’ayan, PhD, Professor of Pharmacological Sciences and Director of the Mount Sinai Center for Bioinformatics at Icahn Mount Sinai.

The team developed a knowledge graph—a descriptive model that maps out the relationships between entities and concepts—called ReproTox-KG to integrate data about small-molecule drugs, birth defects, and genes. In addition to constructing the knowledge graph, the team also used machine learning, specifically semi-supervised learning, to illuminate unexplored links between some drugs and birth defects.

Here’s how ReproTox-KG works as a knowledge graph to predict birth defects.

The study examined more than 30,000 preclinical small-molecule drugs for their potential to cross the placenta and induce birth defects, and identified more than 500 “cliques”—interlinked clusters between birth defects, genes, and drugs—that can be used to explain molecular mechanisms for drug-induced birth defects. Findings were published in Communications Medicine on July 17, and the platform has been made available on a web-based user interface.

In this Q&A, Dr. Ma’ayan, senior author of the paper, discusses ReproTox-KG and its potential impacts.

What was the motivation for your study?

The motivation for the study was to find a use case that combines several datasets produced by National Institutes of Health (NIH) Common Fund programs to demonstrate how integrating data from these resources can lead to synergistic discoveries, particularly in the context of reproductive health.

The study identifies some relationships between approved drugs and birth defects to identify existing drugs that are currently not classified as harmful but which may pose risks to the development of a fetus. It also provides a new global framework to assess potential toxicity for new drugs and explain the biological mechanisms by which some drugs known to cause birth defects may operate.

What are the implications?

Identifying the causes of birth defects is complicated and difficult. But we hope that through complex data analysis integrating evidence from multiple sources, we can improve our understanding of reproductive health and fetal development, and also warn about the potential of new drugs to cause birth defects before these drugs are widely marketed and distributed.

What are the limitations of the study?

We have not yet experimentally validated any of the predictions. There are currently no considerations of tissue and cell type, and the knowledge graph representation omits some detail from the original datasets for the sake of standardization. The website that supports the study may not be appealing to a large audience.

How might these findings be put to use?

Regulatory agencies such as the U.S. Environmental Protection Agency or the Food and Drug Administration may use the approach to evaluate the risk of new drug or other chemical applications. Manufacturers of drugs, cosmetics, supplements, and foods may consider the approach to evaluate the compounds they include in products.

What is your plan for following up on this study?

We plan to use a similar graph-based approach for other projects focusing on the relationship between genes, drugs, and diseases. We also aim to use the processed dataset as training materials for courses and workshops on bioinformatics analysis. Additionally, we plan to extend the study to consider more complex data, such as gene expression from specific tissues and cell types collected at multiple stages of development.

Learn more about how Mount Sinai researchers and clinicians are leveraging machine learning to improve patient lives

However, most AI models for ECG analysis use a particular deep learning method called convolutional neural networks (CNNs). CNNs require large training datasets to make diagnoses, which spell limitations when it comes to rare heart diseases that do not have a wealth of data.

Researchers at the Icahn School of Medicine at Mount Sinai have developed an AI model, called HeartBEiT, for ECG analysis, which works by interpreting ECGs as language.

The model uses a transformer-based neural network, a class of network that is unlike conventional networks but does serve as a basis for popular generative language models, such as ChatGPT.

Here’s how HeartBEiT works as an artificial intelligence deep-learning model, and how it compares to CNNs.

In this Q&A, Dr. Vaid discusses the impact of this new AI model on reading ECGs.

What was the motivation for your study?

Deep learning as applied to ECGs has had much success, but most deep learning studies for ECGs use convolutional neural networks, which have limitations.

Recently, the transformer class of models has assumed a position of importance. These models function by establishing relationships between parts of the data they see. Generative transformer models such as the popular ChatGPT utilize this understanding to generate plain-language text.

By using another generative image model, HeartBEiT creates representations of the ECG that may be considered “words,” and the whole ECG may be considered a single “document.” HeartBEiT understands the relationship between these words within the context of the document, and uses this understanding to perform diagnostic tasks better.

Deployment of this model and its derivatives into clinical practice can greatly enhance the manner in which clinicians interact with ECGs. We are no longer limited to models for commonly seen conditions, since the paradigm can be extended to nearly any pathology.

What is your plan for following up on this study?

We intend to scale up the model so that it can capture even more detail. We also intend to validate this approach externally, in places outside Mount Sinai.

Learn more about how Mount Sinai researchers and clinicians are leveraging machine learning to improve patient lives

Girish Nadkarni, MD, MPH, and Faris Gulamali

Artificial intelligence (AI) and machine learning (ML) have seen increasing use in health care, from guiding clinicians in diagnosis to helping them decide the best course of treatment. However, AI still has much unrealized potential in various health care settings.

Mount Sinai researchers are exploring bringing AI into intensive care, and developed Spatial Resolved Temporal Networks (SpaRTeN), a model to assess high-frequency patient data and generate representations of their state in real time.

The work was presented at the Time Series Representation Learning for Health workshop on Friday, May 5, hosted by the International Conference for Learned Representations, a premier gathering dedicated to machine learning.

Hear from Girish Nadkarni, MD, MPH, Irene and Dr. Arthur Fishberg Professor of Medicine at the Icahn School of Medicine at Mount Sinai and the leader of the SpaRTeN research, and Faris Gulamali, medical student at Icahn Mount Sinai and member of the Augmented Intelligence in Medicine and Science lab, on what lay behind creating the model and what it could achieve for patients.

What was the motivation for your study?

A growing amount of research is indicating the need to redefine critical illness by biological state rather than a non-specific illness syndrome. Advances in genomics, data science, and machine learning have generated evidence of different underlying etiologies for common ICU syndromes. As a result, patients with the exact same diagnosis can have entirely different outcomes.

What are the implications?

In the ICU, representations of a patient can be used to guide personalized treatments based on personalized diagnoses rather than generic treatments with empirical diagnoses.

What are the limitations of the study?

In this study, we only looked at using one type of data at a time in real time. For example, we looked primarily at measures of intracranial pressure. However, the ICU has many types of data being output simultaneously. Future work hopes to integrate all the different types of data such as electrocardiograms, blood pressure, and imaging to improve patient representations.

How might these findings be put to use?

These patient representations are being combined with data on medications and procedures to determine how to optimize patient treatment based on underlying state rather than common illness syndromes.

What is your plan for following up on this study?

In this study, we focused primarily on creating the algorithm and showing that it works for the case of intracranial hypertension. In future studies, we would like to integrate multiple data modalities such as imaging, electrocardiograms, and blood pressure as well as intervention-based data such as medications and procedures to determine precise empirical interventions that lead to improvements in short-term and long-term patient outcomes.

Learn more about how Mount Sinai researchers and clinicians are leveraging machine learning to improve patient lives