An innovative AI-based approach to bone mineral density assessment in psoriasis patients using routine chest X-rays.

Psoriasis is a chronic immune-mediated inflammatory disease that affects both the skin and musculoskeletal system. Recent evidence suggests an elevated risk of low bone mineral density (BMD) in patients with psoriasis. However, BMD assessment is rarely performed in routine clinical practice due to limited access to dual-energy X-ray absorptiometry (DXA). To evaluate BMD in patients with psoriasis using an artificial intelligence (AI)-based tool applied to routine chest radiographs, and to investigate associations with disease duration, disease severity (measured by Psoriasis Area and Severity Index [PASI]), and disease subtype. We retrospectively analysed 132 Japanese patients with psoriasis who underwent chest radiographs prior to initiating biologic therapy between 2010 and 2023. BMD was estimated using an original AI model for predicting BMD on chest radiographs. Patients were categorized as having normal BMD, osteopenia, or osteoporosis based on T-scores. Clinical associations were assessed using statistical methods, including ROC curve analysis to determine cut-off values for disease duration and PASI scores. A higher prevalence of AI-estimated osteoporosis was observed among middle-aged male patients compared to the general population. Longer disease duration (≥seven years, as determined by ROC analysis) was significantly associated with lower AI-estimated BMD (p=0.0032). Although patients with PASI scores ≥10.4 and those with the pustular subtype exhibited trends toward lower BMD, these differences did not reach statistical significance. Our findings indicate a substantial reduction in BMD among male psoriasis patients in their 40s and 50s.