Computer-aided diagnosis based on hand thermal, RGB images, and grip force using artificial intelligence as screening tool for rheumatoid arthritis in women.

Rheumatoid arthritis (RA) is an autoimmune disorder that typically affects people between 23 and 60 years old causing chronic synovial inflammation, symmetrical polyarthritis, destruction of large and small joints, and chronic disability. Clinical diagnosis of RA is stablished by current ACR-EULAR criteria, and it is crucial for starting conventional therapy in order to minimize damage progression. The 2010 ACR-EULAR criteria include the presence of swollen joints, elevated levels of rheumatoid factor or anti-citrullinated protein antibodies (ACPA), elevated acute phase reactant, and duration of symptoms. In this paper, a computer-aided system for helping in the RA diagnosis, based on quantitative and easy-to-acquire variables, is presented. The participants in this study were all female, grouped into two classes: class I, patients diagnosed with RA (n = 100), and class II corresponding to controls without RA (n = 100). The novel approach is constituted by the acquisition of thermal and RGB images, recording their hand grip strength or gripping force. The weight, height, and age were also obtained from all participants. The color layout descriptors (CLD) were obtained from each image for having a compact representation. After, a wrapper forward selection method in a range of classification algorithms included in WEKA was performed. In the feature selection process, variables such as hand images, grip force, and age were found relevant, whereas weight and height did not provide important information to the classification. Our system obtains an AUC ROC curve greater than 0.94 for both thermal and RGB images using the RandomForest classifier. Thirty-eight subjects were considered for an external test in order to evaluate and validate the model implementation. In this test, an accuracy of 94.7% was obtained using RGB images; the confusion matrix revealed our system provides a correct diagnosis for all participants and failed in only two of them (5.3%). Graphical abstract.

Automated flow-through amperometric immunosensor for highly sensitive and on-line detection of okadaic acid in mussel sample.

An electrochemical immunosensor for okadaic acid (OA) detection has been developed, and used in an indirect competitive immunoassay format under automated flow conditions. The biosensor was fabricated by injecting OA modified magnetic beads onto screen printed carbon electrode (SPCE) in the flow system. The OA present in the sample competed with the immobilized OA to bind with anti-okadaic acid monoclonal antibody (anti-OA-MAb). The secondary alkaline phosphatase labeled antibody was used to perform electrochemical detection. The current response obtained from the labeled alkaline phosphatase to 1-naphthyl phosphate decreased proportionally to the concentration of free OA in the sample. The calculated limit of detection (LOD) was 0.15 µg/L with a linear range of 0.19-25 µg/L. The good recoveries percentages validated the immunosensor application for real mussel samples. The developed system automatically controlled the incubation, washing and current measurement steps, showing its potential use for OA determination in field analysis.

An approach to an inhibition electronic tongue to detect on-line organophosphorus insecticides using a computer controlled multi-commuted flow system.

An approach to an inhibition bioelectronic tongue is presented. The work is focused on development of an automated flow system to carry out experimental assays, a custom potentiostat to measure the response from an enzymatic biosensor, and an inhibition protocol which allows on-line detections. A Multi-commuted Flow Analysis system (MCFA) was selected and developed to carry out assays with an improved inhibition method to detect the insecticides chlorpyrifos oxon (CPO), chlorfenvinfos (CFV) and azinphos methyl-oxon (AZMO). The system manifold comprised a peristaltic pump, a set of seven electronic valves controlled by a personal computer electronic interface and software based on LabView® to control the sample dilutions into the cell. The inhibition method consists in the injection of the insecticide when the enzyme activity has reached the plateau of the current; with this method the incubation time is avoided. A potentiostat was developed to measure the response from the enzymatic biosensor. Low limits of detection of 10 nM for CPO, CFV, and AZMO were achieved.