BACKGROUND: Chronic spinal pain is the most prevalent chronic disease, with chronic persistent spinal pain lasting longer than one-year reported in 25% to 60% of the patients. Health care expenditures have been escalating and the financial impact on the US economy is growing. Among multiple modalities of treatments available, facet joint interventions and epidural interventions are the most common ones, in addition to surgical interventions and numerous other conservative modalities of treatments. Despite these increasing costs in the diagnosis and management, disability continues to increase. Consequently, algorithmic approaches have been described as providing a disciplined approach to the use of spinal interventional techniques in managing spinal pain. This approach includes evaluative, diagnostic, and therapeutic approaches, which avoids unnecessary care, as well as poorly documented practices.  Recently, techniques involving artificial intelligence and machine learning have been demonstrated to contribute to the improved understanding, diagnosis, and management of both acute and chronic disease in line with well-designed algorithmic approach. The use of artificial intelligence and machine-learning techniques for the diagnosis of spinal pain has not been widely investigated or adopted. OBJECTIVES: To evaluate whether it is possible to use artificial intelligence via machine learning algorithms to analyze specific data points and to predict the most likely diagnosis related to spinal pain. STUDY DESIGN: This was a prospective, observational pilot study. SETTING: A single pain management center in the United States. METHODS: A total of 246 consecutive patients with spinal pain were enrolled. Patients were given an iPad to complete a Google form with 85 specific data points, including demographic information, type of pain, pain score, pain location, pain duration, and functional status scores. The data were then input into a decision tree machine learning software program that attempted to learn which data points were most likely to correspond to the practitioner-assigned diagnosis. These outcomes were then compared with the practitioner-assigned diagnosis in the chart. RESULTS: The average age of the included patients was 57.4 years (range, 18-91 years). The majority of patients were women and the average pain history was approximately 2 years. The most common practitioner-assigned diagnoses included lumbar radiculopathy and lumbar facet disease/spondylosis. Comparison of the software-predicted diagnosis based on reported symptoms with practitioner-assigned diagnosis revealed that the software was accurate approximately 72% of the time. LIMITATIONS: Additional studies are needed to expand the data set, confirm the predictive ability of the data set, and determine whether it is broadly applicable across pain practices. CONCLUSIONS: Software-predicted diagnoses based on the data from patients with spinal pain had an accuracy rate of 72%, suggesting promise for augmented decision making using artificial intelligence in this setting.