SAN FRANCISCO, BARCELONA, TORONTO – October 31, 2024 – Artificial Intelligence (AI) could play a significant role in aiding the diagnosis of rare diseases. This is especially true for facial recognition and machine learning in a disease like acromegaly (and other pituitary conditions) characterized by remarkable changes in physical appearance.
Acromegaly is often caused by a benign tumor (adenoma) on the pituitary gland, leading to increased growth hormone production. The excess growth hormone causes bones and tissues to enlarge, leading to abnormal growth, especially in the hands, feet, and facial features. The condition develops slowly, often over several years, and can be challenging to diagnose in its early stages. Reducing the time it takes to recognize the disease, presently 6 to 10 years, would mean significant improvements in quality of life and substantial cost reductions. According to NIH studies , acromegaly ranges between 2.8 and 13.7 cases per 100,000 people and is most often diagnosed in middle age.
Technological advancements are poised to revolutionize medical diagnostics by integrating big data and biometrics into routine healthcare practices, enabling physicians to catch conditions at an earlier stage when they are more treatable and reduce the devastating related conditions that come with the disease.
Two potentially groundbreaking programs: the first directed by Dr. Manel Puig Domingo, who is Head of Endocrinology and Nutrition at Germans Trias i Pujol University Hospital and Associate Professor of Endocrinology at the Autonomous University of Barcelona.
“Based on the application of mathematical functions to computational vision analyses,” explains Dr Puig, “we have been able to build a software that explores the facial geometry of the face through specific points of the face we call nodes. The nodes are points that mark the morphological structures that will be modified with the progression of acromegaly, and the variation of their disposition in the facial space is defined as the pattern. These analyses aim to turn subjective information (modifying facial signs clinically visible over time) into numerical data that can be compared objectively (numerical code). Finally, this information proceeds to categorize the photographs using a ranking algorithm based on the degree of similarity with the pattern. The ongoing research focuses on improving diagnostic assistance patterns with the help of processing techniques and machine learning so that every time the computer correctly diagnoses a patient with known acromegaly, it incorporates its image in the database. The more correct the selection of the points, the more sensitive the tool is to detect the disease. Therefore, the contribution offered by the optimized and automatic selection of benchmarks increases the quality of the diagnosis.” Listen to a podcast with Dr. Puig on this work.
The next initiative is directed by Dr. Michael Cusimano, Professor of Neurosurgery, Education and Public Health Division of Neurosurgery, St. Michael’s Hospital, University of Toronto. Dr. Cusimano’s study aims to develop and evaluate a system that can detect Acromegaly and other pituitary diseases, before they lead to significant changes in patient’s physical features like their face or hands and before they develop side effects such as diabetes, high blood pressure, and sleep apnea. Through a survey patients are asked to complete a detailed survey, upload images, and document proof of acromegaly tumors or other pituitary tumors. The survey also encourages patients to invite others to participate. This link will take you to the study if you wish to participate: https://redcap.smh.ca/redcap/surveys/?s=HL9H8EJDJE – For more information, please reach out to Dr. Cusimano or Melissa Fazari, research assistant at acromegaly-research@smh.ca
And stay tuned to Pituitary World News for more details and updates on these initiatives.
About Pituitary World news work on promoting awareness and early diagnosis of pituitary disease: Since its launch in 2014, Pituitary World News (PWN) has emphasized the importance of early diagnosis of pituitary disease to improve quality of life outcomes, reduce comorbidities, and reduce costs. Early detection is crucial because pituitary disease often goes unrecognized for years due to its subtle symptoms, which can lead to severe health issues like cardiovascular problems, diabetes, joint disease, and bone abnormalities. The organization advocates for raising awareness among healthcare providers and the public to reduce the time from symptom onset to diagnosis. Read facial recognition, machine learning and AI content here.
A significant barrier to early diagnosis is the lack of awareness among frontline healthcare professionals who may not immediately associate acromegaly’s symptoms—such as changes in facial features, hand size, and joint pain—with the condition. Increasing education and awareness efforts can help identify the disease earlier, leading to better management and fewer long-term complications.
PWN has promoted various educational resources, including articles, videos, and podcasts, to inform patients and practitioners about recognizing early signs and managing acromegaly effectively. More information here: https://pituitaryworldnews.org
About Dr. Puig and Dr. Cusimano
Dr. Manel Puig Domingo, University of Barcelona is currently Head of Endocrinology and Nutrition at Germans Trias i Pujol University Hospital and Associate Professor of Endocrinology at the Autonomous University of Barcelona. He received his training in endocrinology and diabetes at Hospital de Santa Pau in Barcelona and a postdoctoral fellowship at the University of Texas in San Antonio.
Dr. Michael Cusimano is Professor Temerty Faculty of Medicine, Department of Surgery. He is a graduate of the University of Toronto School of Medicine. He entered the Neurosurgery Training Program at the University of Toronto in 1985 and became a Fellow of the Royal College of Physicians and Surgeons of Canada in 1990. He earned a Master’s Degree in Health Professions Education from the University of Illinois at Chicago also in 1990.
© 2024, Pituitary World News. All rights reserved.