Potential for AI and Machine Learning in Healthcare

Olivia Parlow

I am a hypochondriac. Each month, I convince myself I am dying. I have diagnosed myself with lymphoma, premature heart disease, a brain tumor, and meningitis. I’ve been to urgent care more times than I can count because I am constantly in fear that I am dying. Blood tests, EKGs, echocardiograms, CT scans… The list goes on. You’d imagine being poked and prodded for all these tests is the worst part, but for me the worst part is waiting for the results. Not only do I have to wait to go to my appointment, but then I have to get the test done and wait for sometimes two weeks for the follow-up to go over the results. That’s the worst part. Even though all my health care fears have been disproven, every time I take one of these tests I wonder “What would happen if I really was dying?” “Would I find out two weeks after I bring it to the attention of the doctor?” It makes you wonder if there’s a better, quicker way to analyze these test results. 


In recent years, scientists have been researching a potential tool for faster, more accurate analyses of tests and diagnosis. This tool is AI. The first AI powered medical device was FDA approved in 1995 for cervical slide interpretation. Since then, the FDA has approved over 500 AI enabled medical devices. Researchers are particularly interested in AI and cancer care. 


One way is analyzing medical records using language processing and pattern recognition to identify at-risk patients. These models will look for signs and symptoms indicative of cancer, risk factors based on medical history and patient lifestyle, or other specific health measures associated with cancer. The idea is that the model will recognize patterns of symptoms, signs, and risk factors associated with cancer and be able to highlight patients that should be screened due to their risk factors. This is especially beneficial for cancers that are low incidence, but still have a high mortality rate. It wouldn’t be efficient to screen everyone for these cancers because they are less common, but if machine learning can be used to label patients as “high risk,”  then they can be screened at an earlier stage. 


Another use of AI in cancer screening is image analysis. In 2016, researchers used machine learning for detecting cancerous tissue in lung cancer MRIs. This particular study showed the machine learning algorithm to be 97% accurate in identifying malignant and benign tissue. Another study conducted in 2020 showed that an AI algorithm performed better than National Lung Screening Trial radiologists for detection of pulmonary nodules in digital radiographs. Dr. Toufic Kachaamy states that humans can fall to “inattentional blindness,” meaning they miss significant findings when focused on a specific task. Machines do not experience fatigue, distraction, or inattentional blindness. Therefore, AI could be potentially used in conjunction with a radiologist or doctor to best identify images and make accurate diagnoses. 


There exists great opportunities for AI and Machine Learning to be utilized for good in healthcare, particularly cancer care. Studies on AI and Machine Learning-enabled devices have shown promising results of using these tools for detection and prediction, with the opportunity for improving patient care and making testing quicker and more efficient, a feature that my hypochondriac-self can appreciate. However, I do wonder what some critics of U.S. cancer care, like John Horgan, would say about the incorporation of AI tools into cancer care. Perhaps artificial intelligence can reduce unnecessary testing by only encouraging screening for patients truly at risk or by helping to determine if treatment would do more harm than good if a tumor is identified. I would like to explore this more because there is a possibility that machine learning and AI can potentially increase testing, thus increasing the cost of healthcare and potentially increasing the likelihood of cancer treatment that actually hurts patient outcomes, more than it helps. 



Sources:

An Enhanced k Nearest Neighbor Method to Detecting and Classifying MRI Lung Cancer Images for Large Amount Data, www.researchgate.net/publication/301560176_An_enhanced_k_nearest_neighbor_method_to_detecting_and_classifying_MRI_lung_cancer_images_for_large_amount_data. Accessed 31 Oct. 2023.

Toufic Kachaamy, MD. “Artificial Intelligence and Machine Learning in Cancer Detection.” Targeted Oncology, Targeted Oncology, 4 May 2023, www.targetedonc.com/view/artificial-intelligence-and-machine-learning-in-cancer-detection.

Yoo, Hyunsuk. “Validation of Deep Learning Algorithm for Malignant Pulmonary Nodule Detection in Chest Radiographs.” JAMA Network Open, JAMA Network, 24 Sept. 2020, jamanetwork.com/journals/jamanetworkopen/fullarticle/2770952.

Zhang, Bo, et al. “Machine Learning and AI in Cancer Prognosis, Prediction, and Treatment Selection: A Critical Approach.” Journal of Multidisciplinary Healthcare, U.S. National Library of Medicine, 26 June 2023, www.ncbi.nlm.nih.gov/pmc/articles/PMC10312208/#cit0066.

Comments

Post a Comment

Popular posts from this blog

Molecules, Models, and Magic: The Exciting World of Computational Chemistry

Vrinda Modi I often spend time in a little cubicle in McLean in the freezing corporate cold wrapped in a blanket in the Hoboken summers sipping on free coffee from the office above. It almost always tastes like chalk, but the routine is so embedded in me. Hence, this is the perfect opportunity to talk a little more about my research in computational chemistry here at Stevens and the advances I expect in the next few years. This field excites me because it bridges my interest in chemistry with modern computing techniques, a powerful tool for advancing our understanding of chemical reactions and molecular interactions. This means we are a dry lab – running simulations on computers. No chemicals, no PPE, just models and algorithms. But why does computational chemistry exist in the first place, especially when chemistry is so rooted in physical matter? The answer is efficiency. Modeling molecules on a computer saves us from ordering chemicals, waiting for deliveries (a delay in chemistry t...
Read more

Scaling the Potential of Vertical Farming Going into 2025 and Beyond

Image
  Matthew P Kearney Scaling the Potential of Vertical Farming Going into 2025 and Beyond      Vertical farming may seem like something out of a futuristic movie, but they are very real in today’s agricultural industry. Vertical farming may promote a stronger relationship between urbanization and sustainable crop production. Based on recent innovations across agriculture and technology, vertical farming has the potential to revolutionize our current farming system. Through the development of vertical farming-based production lines, cities and otherwise unfarmable areas can be provided with fresh, local, and pesticide-free produce. Vertical farming and other adaptations of agriculture are not new ideas, but instead a historic and human process.      These technologies are ready to meaningfully address global food security through the technological and computational advancements in agriculture. Vertical farming has a promising future, which becomes a case...
Read more

Knot Your Average Problem: How do Tongue Ties Impact Oral Myofunctional Health?

Image
  Hadia Hussain      Knot Your Average Problem: How do Tongue Ties Impact Oral Myofunctional Health? Sitting in the nursery of the dental office where I worked, I reviewed Baby V’s medical history and reports from the Emergency Department at Jersey City Medical Center. I found it odd that, despite multiple visits and clear signs of malnutrition, no physician had been able to diagnose the cause. Baby V, at a low weight of 12 pounds was struggling with difficulty nursing and bottle feeding, excessive gassiness, colic, clicking sounds when feeding, milk dribbling out of the mouth, and mouth breathing—but doctors had dismissed these signs, labeling him as "healthy."  It didn’t make sense as his low weight raised serious concerns.  According to Pediatric specialists Jenny Olson, DNP, and Sarha DeVrieze, ARNP, at the UnityPoint Clinic, a 9-month-old baby boy should weigh anywhere in between the range of 17 to 25 pounds. Baby V's situation was clearly a ...
Read more