Intention Prediction and Human Health Condition Detection in Reaching Tasks with Machine Learning Techniques.

Detecting human motion and predicting human intentions by analyzing body signals are challenging but fundamental steps for the implementation of applications presenting human-robot interaction in different contexts, such as robotic rehabilitation in clinical environments, or collaborative robots in industrial fields. Machine learning techniques (MLT) can face the limit of small data amounts, typical of this kind of applications. This paper studies the illustrative case of the reaching movement in 10 healthy subjects and 21 post-stroke patients, comparing the performance of linear discriminant analysis (LDA) and random forest (RF) in: (i) predicting the subject's intention of moving towards a specific direction among a set of possible choices, (ii) detecting if the subject is moving according to a healthy or pathological pattern, and in the case of discriminating the damage location (left or right hemisphere). Data were captured with wearable electromagnetic sensors, and a sub-section of the acquired signals was required for the analyses. The possibility of detecting with which arm (left or right hand) the motion was performed, and the sensitivity of the MLT to variations in the length of the signal sub-section were also evaluated. LDA and RF prediction accuracies were compared: Accuracy improves when only healthy subjects or longer signals portions are considered up to 11% and at least 10%, respectively. RF reveals better estimation performance both as intention predictor (on average 59.91% versus the 62.19% of LDA), and health condition detector (over 90% in all the tests).

Quantitative analysis of voluntary movement and anticipatory postural adjustments: a functional approach.

Daily living activities and tasks like standing forward reaching present complex Anticipatory Postural Adjustments (APAs), and an objective, repeatable, subject- and task-dependent procedure to detect Voluntary Movements (VM) and APAs onsets is still missing. This paper proposes a new approach to the VMs study, based on a functional mechanical interpretation of the movement performing, which allows defining kinematic and dynamic APAs. A protocol for the identification of VMs and APAs onsets in the reaching movement is presented. Acquired data on 9 healthy young subjects enable a preliminary validation of this method suitability as support for an objective quantification of APAs.

CD4+CD28- T lymphocytes contribute to early atherosclerotic damage in rheumatoid arthritis patients.

BACKGROUND: Peripheral blood expansion of an unusual CD4+ T-cell subset lacking surface CD28 has been suggested to predispose rheumatoid arthritis (RA) patients to develop more aggressive disease. However, the potential association between CD4+CD28null T cells and early atherosclerotic changes in RA has never been investigated. METHODS AND RESULTS: The number of circulating CD4+CD28null cells was evaluated in 87 RA and 33 control subjects who also underwent evaluation of carotid artery intima-media thickness (IMT) and endothelial function via flow-mediated vasodilation (FMV). Patients had higher IMT and lower FMV compared with control subjects. The frequency of CD4+CD28null cells was significantly higher in patients than in control subjects. Twenty patients with persistent expansion of circulating CD4+CD28null cells had more marked increase of carotid artery IMT and stronger decrease of brachial artery FMV. Blockade of tumor necrosis factor-alpha led to a partial reappearance of the CD28 molecule on the CD4+ cell surface. CONCLUSIONS: Circulating CD4+CD28(null) lymphocytes are increased in RA. Patients with persistent CD4+CD28null cell expansion show preclinical atherosclerotic changes, including arterial endothelial dysfunction and carotid artery wall thickening, more significantly than patients without expansion. These findings suggest a contribution of this cell subset in atheroma development in RA. Moreover, the demonstration that tumor necrosis factor-alpha blockade is able to reverse, at least in part, the CD28 deficiency on the CD4+ cell surface may be of interest for possible innovative therapeutic strategies in cardiovascular diseases.