Could Machine Learning Predict Lupus Hospitalizations?

 

Have you ever heard of machine learning? Machine learning is a form of artificial intelligence (AI) which teaches systems to learn, act, and improve an experience without explicit programming. It can help analyze patterns in data and make predictions based on those patterns. As machine learning has grown in scope and popularity, many have wondered in what ways it might be applicable within the medical field. According to an article from the Lupus Foundation of America, a new study suggests that machine learning can be utilized to predict hospitalization risk relating to lupus. 

The study, published in Lupus, explored the applicability of machine learning for predictive measures. To begin, the researchers sourced data from around 2,000 people with lupus. According to the study authors:

Candidate predictors were derived from structured EHR features, including demographics, laboratory tests, medications, ICD-9/10 codes for SLE manifestation, and healthcare utilization.

Ultimately, the machine learning platform was able to determine which factors most highly predicted potential hospitalization. These included albumin and complement C3 levels, the presence of dsDNA antibodies, red and white blood cell levels, and inflammatory markers. 

While this does show promise, more research is needed to determine how much benefit machine learning could bring to the diagnostic process.

About Lupus

Lupus, or systemic lupus erythematosus (SLE), is a chronic autoimmune disorder in which the immune system mistakenly attacks tissues and organs such as the joints, heart, lungs, brain, blood cells, and kidneys. Risk factors for lupus include a family history of autoimmune diseases, being female, being between 15-45 years old, and being of Hispanic/Latino, African American, or Asian American descent. Symptoms of lupus – and presentation – vary greatly between those affected. Some individuals may have severe symptoms while others have mild symptoms. For some, symptoms come and go, while others feel them constantly. These symptoms can include: 

  • A red, butterfly-shaped rash in the center of the face
  • Extreme and sometimes debilitating fatigue
  • Low-grade fevers
  • Shortness of breath 
  • Chest and joint pain
  • Hair loss
  • Confusion and/or memory loss
  • Headaches
  • Skin lesions which worsen with sun exposure
  • Raynaud’s phenomenon
Jessica Lynn

Jessica Lynn

Jessica Lynn has an educational background in writing and marketing. She firmly believes in the power of writing in amplifying voices, and looks forward to doing so for the rare disease community.

Follow us