Posted in | News | Medical Robotics

AI System Unveils New Approach to Rare Disease Diagnosis

Investigators at Baylor College of Medicine developed a new AI system called AI-MARRVEL (AIM) that helps doctors diagnose rare genetic diseases more quickly and accurately. The research was published in the journal NEJM AI.

The AIM module can contribute to predictions independent of clinical knowledge of the gene of interest, according to researchers from the Baylor Genetics clinical diagnostic laboratory. This helps to advance the discovery of novel disease mechanisms.

 The diagnostic rate for rare genetic disorders is only about 30 %, and on average, it is six years from the time of symptom onset to diagnosis. There is an urgent need for new approaches to enhance the speed and accuracy of diagnosis.

Dr. Pengfei Liu, Co-Corresponding Author and Associate Professor, Molecular and Human Genetics, Baylor College of Medicine

Dr. Pengfei Liu is also an Associate Clinical Director at Baylor Genetics.

The Baylor team's Model organism Aggregated Resources for Rare Variant ExpLoration (MARRVEL), a public database of known variants and genetic analysis, is used to train AIM. More than 3.5 million variants from thousands of diagnosed cases are included in the MARRVEL database.

Researchers send AIM the exome sequence data and symptoms of their patients, and AIM returns a ranking of the most likely gene candidates responsible for the uncommon disease.

The performance of AIM was compared with other algorithms found in recent benchmark papers by researchers. Three data cohorts with confirmed diagnoses from Baylor Genetics, the Undiagnosed Diseases Network (UDN), funded by the National Institutes of Health and the Deciphering Developmental Disorders (DDD) project, were used to test the models.

Using these real-world data sets, AIM consistently ranked diagnosed genes as the top candidate in twice as many cases as all other benchmark methods.

We trained AIM to mimic the way humans make decisions, and the machine can do it much faster, more efficiently, and at a lower cost. This method has effectively doubled the rate of accurate diagnosis.

 Dr. Zhandong Liu, Associate Professor and Co-Corresponding Author, Baylor Genetics

Dr. Zhandong Liu is also an investigator at the Jan and Dan Duncan Neurological Research Institute (NRI) at Texas Children’s Hospital.

For rare disease cases that have languished unsolved for years, AIM also provides fresh hope. Every year, hundreds of new disease-causing variants are discovered, which could be crucial to cracking these cold cases.

Nevertheless, the large number of cases makes it difficult to decide which ones must be reanalyzed. Using a dataset of UDN and DDD cases, the researchers tested AIM's clinical exome reanalysis and discovered that it could correctly identify 57 % of cases that could be diagnosed.

Zhandong Liu said, “We can make the reanalysis process much more efficient by using AIM to identify a high-confidence set of potentially solvable cases and pushing those cases for manual review; we anticipate that this tool can recover an unprecedented number of cases that were not previously thought to be diagnosable.”

The researchers also investigated the potential of AIM to identify new gene candidates unrelated to disease. In two UDN cases, AIM accurately identified two recently discovered disease genes as the leading candidates.

AIM is a major step forward in using AI to diagnose rare diseases. It narrows the differential genetic diagnoses down to a few genes and has the potential to guide the discovery of previously unknown disorders.

Dr. Hugo Bellen, Distinguished Service Professor and Co-Corresponding Author, Molecular and Human Genetics, Baylor Genetics

Dr. Hugo Bellen is also the Chair in Neurogenetics at the Duncan NRI.

When combined with the deep expertise of our certified clinical lab directors, highly curated datasets, and scalable, automated technology, we are seeing the impact of augmented intelligence to provide comprehensive genetic insights at scale, even for the most vulnerable patient populations and complex conditions,” states Dr. Fan Xia, Associate Professor and Study Senior Author at Baylor Genetics.

Dr. Fan Xia, who is also the Vice President of Clinical Genomics at Baylor Genetics, adds, “By applying real-world training data from a Baylor Genetics cohort without any inclusion criteria, AIM has shown superior accuracy. Baylor Genetics is aiming to develop the next generation of diagnostic intelligence and bring this to clinical practice.”

Co-authors include Dongxue Mao, Chaozhong Liu, Linhua Wang, Rami AI-Ouran, Cole Deisseroth, Sasidhar Pasupuleti, Seon Young Kim, Lucian Li, Jill A.Rosenfeld, Linyan Meng, Lindsay C. Burrage, Michael Wangler, Shinya Yamamoto, Michael Santana, Victor Perez, Priyank Shukla, Christine Eng, Brendan Lee and Bo Yuan.

They are affiliated with one or more of the following institutions: Baylor College of Medicine, Jan and Dan Duncan Neurological Research Institute at Texas Children’s Hospital, Al Hussein Technical University, Baylor Genetics, and the Human Genome Sequencing Center at Baylor.

This work was funded by the Chang Zuckerberg Initiative and the National Institute of Neurological Disorders and Stroke.

Journal Reference:

Mao, D. et al. (2024) AI-MARRVEL – A Knowledge-Driven AI System For Diagnosing Mendelian Disorders. NEJM AI. doi.org/10.1056/Aioa2300009.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.