An autoimmune disease is a condition in which your immune system mistakenly attacks your body. According to the Autoimmune Registry Inc. first comprehensive list of autoimmune diseases published in 2020, between 15 and 30 million people in the United States suffer from autoimmune diseases. It is the nation’s largest class of illness, and it primarily affects women aged 20 to 40. Traditional therapies for autoimmune diseases have relied on corticosteroids and other immunosuppressive medications to reduce inflammation and suppress the immune system. While corticosteroids and immunosuppressants are highly effective for many patients, long term use can have a significant impact on quality of life. This has led to a push for the development of more specific treatments that lower the risk of systemic immune suppression and improve tolerability. Patient-Reported Outcome Measures (PROMs) are increasingly being collected in clinical practice to monitor quality of care and improve treatment decision processes. The shifting focus from disease-specific factors toward the patient perspective may provide a useful basis for shared medical decision-making between clinician and patient. Utilization of machine learning may provide a promising avenue for enhancing the usefulness of PROMs. By using PROMs as a benchmark for improvement, machine learning models can predict which patient may improve from a treatment or procedure. Machine learning algorithms can be used to help patients and physicians in shared treatment decisions. The purpose of this project is to explore whether machine learning models can be used to predict the clinical outcomes for patients with autoimmune diseases.