Machine learning based analysis of biochemical and morphologic parameters in patients with dialysis related amyloidosis

Barišić, Igor; Wilhelm, Vladimir; Štambuk, Nikola; Karaman, Ksenija; Janković, Stipan; Konjevoda, Paško; Pokrić, Biserka (2002) Machine learning based analysis of biochemical and morphologic parameters in patients with dialysis related amyloidosis. Croatica Chemica Acta, 75 (4). pp. 935-944. ISSN 0011-1643

PDF - Published Version
Download (73kB)

Official URL: http://public.carnet.hr/ccacaa/co024.html

Abstract

Dialysis related amyloidosis is the accumulation and deposition of beta(2)-microglobulin derived fibrils in bones and joints, due to insufficient elimination during therapy or slowly progressing renal failure. The aim of this study was to analyse biochemical, morphologic and anamnestic parameters that may be relevant for the onset and developement of dialysis related amyloidosis. In addition to standard statistical procedures, we also applied the machine-learning based methods of data mining to quantify the risk factors for asymptomatic patients. Extraction of: risk factors for the onset of the dialysis related amyloidosis syndrome could enable the clinician to predict the symptoms and consider medical procedures to prevent the onset of the disease. The C4.5 machine learning algorithm extracted a simple and highly accurate tree for discrimination of asymptomatic and symptomatic patients suffering from dialysis related amyloidosis. It remains an open question if our findings may contribute to the problem of accurately predicting the onset of dialysis related arthropathy in the asymptomatic patient group.

Item Type:

Article

Uncontrolled Keywords:

dialysis; amyloidosis; biochemistry; morphologic parameters; shoulder; knee; symptoms; glycation end-products; chronic-hemodialysis; sonographic findings; arthropathy; ultrasound; diagnosis; shoulder

Subjects:

NATURAL SCIENCES > Chemistry

Divisions:

Division of Molecular Medicine
NMR Center

Projects: