AI in Research & Healthcare

The first theory of artificial intelligence (AI) came into existence in the 1950s, when Alan Turing released his publication titled Computing Machinery and Intelligence. Turing, who is widely considered the father of theoretical computer science, created a framework that sparked a technological evolution that resulted in the computers and AI we use today. Since the publication of this paper 73 years ago, AI has transformed from a theoretical concept to a staple in our everyday lives. In honor of the Alliance for Artificial Intelligence in Healthcare (AAIH) Annual Members Meeting, today’s digest explores the applications of AI and ML in the research and healthcare setting, highlighting their impact and future directions.

What exactly is artificial intelligence? AI refers to the development of computer systems capable of perceiving, synthesizing, and inferring information. Recognizable examples include smart assistants such as Alexa and Siri, chatbots such as ChatGPT and Bard, and self-driving cars. A subset of AI that has transformed productivity and efficiency is known as machine learning (ML), and it involves training computer algorithms to learn from data and make predictions. AI and ML have been used in countless ways in the medical community, with particularly exciting breakthroughs in the areas of early disease detection, precision medicine, and drug discovery.

Early Disease Detection and Precision Medicine

In recent years, AI and ML have made significant strides, empowering researchers and healthcare professionals to better analyze intricate data, make accurate predictions, and develop innovative solutions. ML algorithms, specifically, excel in analyzing medical data that can assist with early disease detection and precision medicine. Although ML is still in its infancy, studies have shown how algorithms can learn to identify subtle anomalies and patterns associated with various diseases by studying patient datasets such as genetic information and imaging (i.e. X-ray, CT, and MRI scans). Ultimately, ML has the potential to assist healthcare professionals in detecting diseases earlier—when interventions are most effective—and can significantly improve patient outcomes.

A fascinating example of the capabilities of ML in diagnostics and precision medicine can be found in the research being conducted at Tulane’s School of Medicine. Dr. Hong-Wen Deng, Chief of the Division of Biomedical Informatics & Genomics and Director of the Center for Biomedical Informatics & Genomics, is working to improve colorectal cancer diagnostics. In a recent study published in Nature Communications, Deng and collaborators used a semi-supervised learning method to develop a machine-assisted pathological recognition program that detects colorectal cancer in patient samples. The researchers found that their program slightly outperformed manual interpretation by pathologists in detecting colorectal cancer. These promising results are particularly significant as there is a global shortage of pathologists, and the intense workload they face can lead to unintentional misdiagnoses. Moreover, this study highlights ways in which AI and ML can be used in a clinical setting to reduce cost, reduce clinician workload, and ultimately save patients time and money.

Drug Discovery and Development

In addition to aiding precision medicine and diagnostics, ML has the potential to revolutionize the way we discover and develop new drugs. By analyzing vast amounts of molecular and biological data, ML algorithms can pinpoint potential drug candidates. These algorithms learn from existing drug-target interactions, allowing them to predict the effectiveness and safety of new compounds. This means less time and money spent on experimental testing, resulting in faster drug discovery and the development of targeted therapies for a wide range of diseases.

Numerous companies, such as Atomwise and Recursion Pharmaceuticals are currently using ML for accelerated drug discovery with promising results. Atomwise has had various successes collaborating with academic centers to accelerate the drug discovery process—including a recent partnership with Tulane—where they use ML to identify compounds that target specific receptors. Recursion Pharmaceuticals is also finding success by utilizing advanced lab robotics and automation to conduct up to 1.5 million experiments per week in the realm of cellular-level disease modeling. Due to their work in AI and ML, they currently have four drug candidates in clinical trials. These two examples barely scratch the surface of the many studies being conducted in this space and highlight the great potential of utilizing AI in drug discovery research.

Current and Future Challenges

While AI/ML brings significant advantages to the field of drug discovery and development, it also comes with its own set of challenges. Ethical concerns, security concerns, and algorithmic biases need to be addressed. To tackle these issues, the FDA has published a discussion paper titled “Using Artificial Intelligence and Machine Learning in the Development of Drug and Biological Products.” This paper aims to foster meaningful conversations among stakeholders, including pharmaceutical companies, ethicists, patients, and regulatory authorities. The paper emphasizes the importance of human involvement, risk-based evaluations, and ongoing performance monitoring of AI/ML models. The FDA emphasizes the need for collaboration and engagement within the biomedical community to fully harness the potential of AI/ML while effectively addressing challenges.

As for the space of precision medicine and diagnostics, a recent analysis conducted by Rutgers highlights a challenge in the field of AI/ML: there is currently no single AI software program that can be used for all treatments. The analysis studied 32 precision medicine AI programs, finding the field is rapidly advancing but highly disorganized. The analysis calls for improved data standardization to help speed up the advancements of this approach.


The integration of AI and ML has the potential to completely transform research and healthcare. ML algorithms empower researchers and healthcare professionals to make more accurate predictions, offer personalized care, and improve patient outcomes. As AI and ML continue to advance, their integration into early disease detection, precision medicine, and drug discovery will unlock new possibilities, propelling scientific discovery forward and enhancing the delivery of high-quality healthcare services. Tulane Medicine is proud to be a part of this movement as one of only 3 University members of the AAIH, and the only one represented on the Executive Committee of the Board. Reach out to us directly for more information on the AAIH, or to enquire about how to become a member.


Curated Research and Research-Related News Summaries, Analysis, and Synthesis. Published on behalf of The Tulane University School of Medicine. Content is generated by reviewing scientific papers and preprints, reputable media articles, and scientific news outlets. We aim to communicate the most current and relevant scientific, clinical, and public health information to the Tulane community – which, in keeping with Tulane’s motto, “Not for Oneself but for One’s Own”, is shared with the entire world.

Kaylynn J. Genemaras, PhD: Editor-in-Chief

Maryl Wright Ponds, MS: Research and Writing Assistance

Special thanks to James Zanewicz, JD, LLM, RTTP, and Elaine Hamm, PhD, for copyediting assistance

Share The Science: Please forward this issue and encourage others to sign up for Tulane School of Medicine’s Digest Mailing List.