Application of machine learning algorithms in building health diagnostics: predictive analytics evaluating indoor air quality and sick building syndrome in educational settings.

OBJECTIVES: To investigate nailfold videocapillaroscopy (NVC) abnormalities in mixed connective tissue disease (MCTD).

METHODS: Patients with MCTD followed at the Rheumatology Department in Cochin Hospital (Paris, France) were identified based on individual record review. Diagnosis of MCTD required fulfillment of one of the three sets of classification criteria. Clinical and laboratory data were collected and NVC was performed on 4 fingers of both hands by one assessor. NVC patterns were analysed by two independent observers.

RESULTS: We identified 51 MCTD patients [mean age 51±12 years, 86% female, 31% had interstitial lung disease (ILD)]. NVC images were available for 40 patients. Three different NVC patterns were identified: 'normal' (15 %); 'non-specific microangiopathy' (40%) and 'scleroderma pattern' (45%). 'Scleroderma pattern' was associated with skin sclerosis (9/18 vs. 5/32; p=0.008) and digital ulcers (6/18 vs. 2/32; p=0.017). We observed a reduction in the number of capillaries in patients with ILD (4.80±1.87 vs. 6.03±1.47; p=0.039). Patients with severe reduction of capillary density (≤4/mm) were more likely to have ILD (5/7 vs. 5/33; p=0.002). Neoangiogenesis was more frequent in patients with ILD (6/13 vs. 4/27; p=0.034). The association between severe reduction of capillary density and ILD was observed independently of the presence of the 'scleroderma pattern' and skin sclerosis.

CONCLUSIONS: We identified three NVC patterns in MCTD patients. 'Scleroderma pattern' was associated with presence of skin sclerosis and digital ulcers. Severe capillary loss was significantly associated with the presence of ILD. Our results indicates that NVC may be helpful for disease risk stratification in MCTD.