Urinary Colorimetric Sensor Array and Algorithm to Distinguish Kawasaki Disease from Other Febrile Illnesses

Abstract

ObjectivesKawasaki disease (KD) is an acute pediatric vasculitis of infants and young children with unknown etiology and no specific laboratory-based test to identify. A specific molecular diagnostic test is urgently needed to support the clinical decision of proper medical intervention, preventing subsequent complications of coronary artery aneurysms. We used a simple and low-cost colorimetric sensor array to address the lack of a specific diagnostic test to differentiate KD from febrile control (FC) patients with similar rash/fever illnesses.Study DesignDemographic and clinical data were prospectively collected for subjects with KD and FCs under standard protocol. After screening using a genetic algorithm, eleven compounds including metalloporphyrins, pH indicators, redox indicators and solvatochromic dye categories, were selected from our chromatic compound library (n = 190) to construct a colorimetric sensor array for diagnosing KD. Quantitative color difference analysis led to a decision-tree-based KD diagnostic algorithm.ResultsThis KD sensing array allowed the identification of 94% of KD subjects (receiver operating characteristic [ROC] area under the curve [AUC] 0.981) in the training set (33 KD, 33 FC) and 94% of KD subjects (ROC AUC: 0.873) in the testing set (16 KD, 17 FC). Color difference maps reconstructed from the digital images of the sensing compounds demonstrated distinctive patterns differentiating KD from FC patients.ConclusionsThe colorimetric sensor array, composed of common used chemical compounds, is an easily accessible, low-cost method to realize the discrimination of subjects with KD from other febrile illness.

Diagnosis support systems for rare diseases: a scoping review

“…Associations of different algorithms, such as fusion algorithms, were encountered in 2 studies [52,53]. Other authors reported using more traditional statistical modeling, such as regression [24] or decision trees [42,60]. The K Nearest Neighbors algorithm was used in 2 studies [51,72].…”

“…The protocol to evaluate and validate the developed models was highly study-dependent and is detailed in the next subsections. The following characteristics were considered: Hybrid (7 studies) Yes [27,[73][74][75][76]78] No [25] Data driven (1 study) Yes [72] Fluids (12 studies) Hybrid (2 studies) Yes [28,29] Data driven (10 studies) Yes [20,23,24,31,36,42,47,48,56,60] Images (16 studies) Hybrid (2 studies) Yes [41,45] Data driven (14 studies) Yes [19, 21, 22, 30, 33-35, 43, 44, 49, 51, 57, 59, 62] Questionnaires (3 studies) Data driven (3 studies) Yes [52,53,58] Family history and combined material (8 studies) Knowledge-based (5 studies) No [26,32,38,46,50] Hybrid (2 studies) Yes [37,39] Data driven (1 study) Yes [40] References are listed in column "articles" according to the type of material considered and the model used (presence/absence of prior knowledge and of machine learning). The number of studies according to material and knowledge is given in parentheses Fig.…”

Image Segmentation Algorithm of Colorimetric Sensor Array Based on Fuzzy C-Means Clustering

“…In the smallest case, the optimal image segmentation is achieved [7,8]. e main difficulty lies in how to effectively determine the initial clustering conditions [9]. e fuzzy membership degree theory proposed by the FCM algorithm matches the characteristics of image information ambiguity very well, considering that the array image is a two-dimensional lattice image with different color information, and segmentation using image information is the main segmentation method of the FCM algorithm [10,11].…”