Artificial Intelligence (AI) and quickly evolving machine learning (ML) methods have been making headlines in 2023, with most of them questioning AI's potential to displace humans in the workplace, its possible ethical implications, and conceivable biases inherent in the information it receives. Built by scientists over decades of trial and error, AI is coming into its own as a powerful ally in the scientific community, especially in the research and treatment of rare diseases that afflict nearly 400 million people worldwide.(1) Dr. Harsha Rajasimha, Founder and Executive Chairman of IndoUSrare, advocates for diversity in clinical trials in order to take full advantage of AI's global reach in the diagnostic odyssey, data science, and clinical trials for rare diseases.
HERNDON, Va., Sept. 5, 2023 /PRNewswire-PRWeb/ -- AI algorithms can swiftly detect patterns and connections that human analysts may miss, aiding in predictive modeling for disease progression and targeted treatments. AI also shows promise in drug development. Dr. Harsha Rajasimha, Founder and Executive Chairman of the Indo-US Organization for Rare Diseases (IndoUSrare), a not-for-profit organization that seeks to bridge the gap that exists in the world when it comes to rare diseases, submits that "The enormity of AI's current and future contributions in accelerating rare disease research is being undermined by a lack of racial, ethnic, and genetic diversity in the patient population being studied, which can sabotage the authenticity of clinical trial outcomes."
Diagnosing rare diseases remains challenging globally due to the lack of most patients' medical records in electronic formats ready for consumption by AI/ML algorithms. In the US, a disease is considered rare if it affects fewer than 200,000 people.(2) Such a limited patient sampling prevents statistically significant parameters for research. Genetic and environmental factors further complicate patient prognoses. AI can assist by analyzing vast amounts of data to identify characteristic patterns and markers of specific rare diseases, reducing diagnosis time and costs. Typical rare disease diagnoses involve medical histories, physical examinations, and genetic testing. AI-powered diagnostic tools can streamline this process by identifying potential diagnoses faster and more accurately. Various ML techniques are being developed to standardize and share medical information, improving interoperability in the field of rare diseases.(3)
Approximately 80% of rare diseases are estimated to have a genetic origin.(4) Dysmorphology is a clinical genetics discipline that studies and interprets patterns of human growth and structural defects, encompassing malformation, disruption, deformation, and dysplasia.(5) "Phenotype" pertains to the observable physical properties of an organism, including its appearance, development, and behavior.(6) AI can analyze and interpret this visible data (e.g., from photos or images) to quickly detect physical markers that may indicate the pathology of certain rare diseases.
Around 40% of rare diseases show craniofacial changes aiding early diagnosis, such as in the eyebrows, nose, and cheeks. Previously, visual evaluation and basic measurements were used, but now AI can provide even more objective methods. However, AI algorithms mostly rely on European and North American databases, overlooking global diversity.(7)
An advanced AI system, such as "GestaltMatcher," can utilize and link facial traits and features with clinical symptoms and genetic data, serving as a starting point for accurate diagnoses with high precision. It requires fewer patients for feature matching, a significant advantage for ultra-rare diseases with limited cases worldwide. Doctors will soon be able to use AI on smartphones for differential diagnoses, complementing their expertise.(8)
AI/ML algorithms efficiently analyze genetic datasets, swiftly identifying disease-causing variants without requiring time-consuming manual interpretation. By incorporating diverse data sources and human genomic expertise, these AI systems learn to predict candidate variants for undiagnosed genetic disorders, providing valuable insights to genetics and precision medicine researchers. This revolutionary approach enables experts to make rapid, precise, and groundbreaking diagnoses, not only of known disease-causing variants but also aid in the discovery of novel causal variants, ultimately improving patient outcomes.(9)
Genomic studies have predominantly utilized samples from people of European ancestry, neglecting the opportunity to learn from larger and more genetically diverse populations, particularly in Asia, which comprises 59.5% of the world's population. This exclusion impedes the equitable advancement of genomic medicine, leading to persistent uncertainty concerning the genetic basis and epidemiology of diseases across various populations and disparities in drug reactions, treatment outcomes, and overall health. Similarly, in immunogenomics research, a lack of diversity hinders the discovery of novel genetic traits associated with immune system phenotypes, both common and distinct across populations. The underrepresentation of non-Caucasian populations from genomics research, understanding how pathogens have applied selective pressures on immune-related genes in diverse environments, and the subsequent manifestation of infectious diseases remains incomplete.(10)
Dr. Rajasimha urges, "So much has already been accomplished with AI advancements and innovation. Intelligent technologies can cast a wider net for more diverse patient recruitment and facilitate the completion of global clinical trials. Inherent biases can be removed through better AI training with more inclusive and heterogeneous datasets. It's worrisome that we are training far too many AI and ML models for rare disease research with biased datasets from only 10% of the world's population residing in the global north, to begin with. Awareness plays a pivotal role in this, and all members along the research continuum share the responsibility to promote cross-cultural collaboration to help ensure the inclusion of all patients with rare and common diseases representative of all humans globally."
The IndoUSrare Corporate Alliance unites biopharmaceutical, diagnostics, medical devices, CROs, and other life science companies to advance orphan product development. Their mission is to collaborate to address common challenges impacting the industry in the pre-competitive space to educate, empower, and advocate for rare disease patients in the United States, India, and globally. By fostering collaboration, global diversity, and pooling resources, the alliance aims to accelerate diagnostics and therapies and bridge critical gaps in affordable research and development through cross-border partnerships.
Join the conversation at the "Digitization of Rare Diseases" session at the upcoming Indo US Bridging RARE Summit 2023. Register Now!
October 29–30, 2023.
On the evening of Sunday, October 29th, the summit will honor eminent leaders for fostering cross-border collaborations in rare diseases between the US and India at a Gala dinner at the Arlington, VA, campus of George Mason University.
About IndoUSrare
IndoUSrare is a humanitarian nonprofit 501(c)(3) tax-exempt public charity organization based in the United States. Founder and Executive Chairman Dr. Harsha Rajasimha, who lost a child to a rare disease in 2012, has been a rare disease advocate for more than 10 years. To address the unmet needs of diverse patients with rare diseases globally, the leadership team comprised of experienced professionals from research, advocacy, regulatory, and drug development seeks to build cross-border collaborations connecting stakeholders of rare diseases in low- and middle-income regions such as India, with their counterparts and clinical researchers in the United States to improve the diversity of clinical trial participants, accelerate research and development, and improve equitable access to life-saving therapies to diverse populations of rare disease patients. Visit https://indousrare.org.
References:‥
1. U.S. Department of Health and Human Services. (2023, March 21). Rare disease day at NIH 2023: Putting hope into action. National Center for Advancing Translational Sciences. ncats.nih.gov/pubs/features/rare-disease-day-at-NIH-2023-putting-hope-into-action#:~:text=Rare%20diseases%20are%20individually%20rare,nearly%20400%20million%20people%20worldwide.
2. Commissioner, O. of the. (n.d.). Rare diseases at FDA. U.S. Food and Drug Administration. fda.gov/patients/rare-diseases-fda.
3. Visibelli, A., Roncaglia, B., Spiga, O., Santucci, A. (2023, March 13). The impact of Artificial Intelligence in the Odyssey of rare diseases. MDPI. mdpi.com/2227-9059/11/3/887.
4. Frederiksen, S. D., Avramovi;#263;, V., Maroilley, T., Lehman, A., Arbour, L., Tarailo-Graovac, M. (2022, February 22). Rare disorders have many faces: In silico characterization of rare disorder Spectrum - Orphanet Journal of rare diseases. BioMed Central. ojrd.biomedcentral.com/articles/10.1186/s13023-022-02217-9#:~:text=Approximately%2080%25%20of%20rare%20diseases,to%20have%20a%20genetic%20origin.
5. Hunter, A. G. W. (2002, August 20). Medical genetics: 2. the diagnostic approach to the child with dysmorphic signs. CMAJ‥: Canadian Medical Association journal = journal de l'Association medicale canadienne. ncbi.nlm.nih.gov/pmc/articles/PMC117854/#:~:text=The%20term%20dysmorphic%20is%20derived,human%20growth%20and%20structural%20defects.
6. Nature Publishing Group. (n.d.). Nature news. nature.com/scitable/definition/phenotype-phenotypes-35/#:~:text=The%20term%20%22phenotype%22%20refers%20to,environmental%20influences%20upon%20these%20genes.
7. Henderson, R. by E. (2023, May 11). AI algorithms for rare disease diagnosis ignore the genetic, morphological diversity of humans. News. news-medical.net/news/20230510/AI-algorithms-for-rare-disease-diagnosis-ignore-the-genetic-morphological-diversity-of-humans.aspx.
8. Shawn, A. (2022, February 11). Researchers use artificial intelligence to detect rare diseases even more accurately - sciencedaily. Verve times. vervetimes.com/researchers-use-artificial-intelligence-to-detect-rare-diseases-even-more-accurately-sciencedaily/.
9. Contributor, E. (2022, December 13). Artificial Intelligence: A new era in rare genetic disease diagnosis. Labiotech.eu. labiotech.eu/opinion/rare-disease-diagnosis-ai/.
10. Peng, K., Safonova, Y., Shugay, M., Popejoy, A. B., Rodriguez, O. L., Breden, F., Brodin, P., Burkhardt, A. M., Bustamante, C., Cao-Lormeau, V.-M., Corcoran, M. M., Duffy, D., Fuentes-Guajardo, M., Fujita, R., Greiff, V., Jönsson, V. D., Liu, X., Quintana-Murci, L., Rossetti, M., … Mangul, S. (2021, May 17). Diversity in immunogenomics: The value and the Challenge. Nature News. nature.com/articles/s41592-021-01169-5.
Media Contact
Karla Jo Helms, JOTO PR™, 727-777-4619, [email protected], jotopr.com
SOURCE IndoUSrare
Share this article