Sarcopenia Diagnostic Technique Based on Artificial Intelligence Using Bio-signal of Neuromuscular System: A Proof-of-Concept Study.

In this paper, we propose an artificial intelligence (AI)-based sarcopenia diagnostic technique for stroke patients utilizing bio-signals from the neuromuscular system. Handgrip, skeletal muscle mass index, and gait speed are prerequisite components for sarcopenia diagnoses. However, measurement of these parameters is often challenging for most hemiplegic stroke patients. For these reasons, there is an imperative need to develop a sarcopenia diagnostic technique that requires minimal volitional participation but nevertheless still assesses the muscle changes related to sarcopenia. The proposed AI diagnostic technique collects motor unit responses from stroke patients in a resting state via stimulated muscle contraction signals (SMCSs) recorded from surface electromyography while applying electrical stimulation to the muscle. For this study, we extracted features from SMCS collected from stroke patients and trained our AI model for sarcopenia diagnosis. We validated the performance of the trained AI models for each gender against other diagnostic parameters. The accuracy of the AI sarcopenia model was 96%, and 95% for male and females, respectively. Through these results, we were able to provide preliminary proof that SMCS could be a potential surrogate biomarker to reflect sarcopenia in stroke patients.

Structural Integrity of the Cerebellar Outflow Tract Predicts Long-Term Motor Function After Middle Cerebral Artery Ischemic Stroke.

BACKGROUND: The cerebellum plays a crucial role in functional movement by influencing sensorimotor coordination and learning. However, the effects of cortico-cerebellar connectivity on the recovery of upper extremity motor function after stroke have not been investigated. We hypothesized that the integrity of the cortico-cerebellar connections would be reduced in patients with a subacute middle cerebral artery (MCA) stroke, and that this reduction may help to predict chronic upper extremity motor function. METHODS: We retrospectively analyzed the diffusion-tensor imaging of 25 patients with a subacute MCA stroke (mean age: 62.2 ± 2.7 years; 14 females) and 25 age- and sex-matched healthy controls. We evaluated the microstructural integrity of the corticospinal tract (CST), dentatothalamocortical tract (DTCT), and corticopontocerebellar tract (CPCT). Furthermore, we created linear regression models to predict chronic upper extremity motor function based on the structural integrity of each tract. RESULTS: In stroke patients, the affected DTCT and CST showed significantly impaired structural integrity compared to unaffected tracts and the tracts in controls. When all models were compared, the model that used the fractional anisotropy (FA) asymmetry indices of CST and DTCT as independent variables best predicted chronic upper extremity motor function (R2 = .506, P = .001). The extent of structural integrity of the CPCT did not significantly differ between hemispheres or groups and was not predictive of motor function. CONCLUSIONS: We found evidence that microstructural integrity of the DTCT in the subacute phase of an MCA stroke helped to predict chronic upper extremity motor function, independent of CST status.

Changes in Trunk Muscle Activity during Unilateral Weight Bearing and Abnormal Postural Gait in Healthy Individuals.

Background and Objectives: Many people tend to carry their bags or baggage on only one side of their body. Due to smartphone use, people also tend to walk bent forward in a kyphotic posture. In this study, we aimed to assess trunk muscle activity changes due to weight-bearing, carried in the left or right hand, and using three different gait postures. Materials and Methods: We recruited 27 healthy participants (aged 19−75 years) with no history of LBP within the last 6 months before study participation. Electromyographic activities of the lower back and the abdominal muscles of the participants were evaluated using four-channel surface electromyography (EMG). Surface EMG recordings were obtained from four trunk muscles, including the flexor (rectus abdominis (RA), external oblique (EO)) and extensor muscles (lumbar erector spinae (LE), and the superficial lumbar multifidus (LM)), during unilateral weight-bearing tasks and with different gait postures (normal gait, with a sway back, and thoracic kyphosis). Results: In the "unilateral weight-bearing task", there was a significant difference in the activity of all the trunk muscles between the weight-bearing limb side and the opposite side (p < 0.05). The activation of the left trunk muscle was greater than that of the right trunk muscle when the dumbbell was lifted using the right hand. The other side showed the same result. In the "gait posture task" performed by the participants using a sway-back posture, the RA and EO had a higher level of activity in the stance and swing phases compared with that in a neutral gait (p < 0.05). Moreover, in the participants with a thoracic kyphosis posture, the LE and LM had a higher level of activity compared with that in a neutral gait (p < 0.05). Conclusions: Our results indicate that abnormal gait posture and unilateral weight-bearing tasks may impair the balance of trunk muscles, increasing the incidence of LBP. However, further large-scale, prospective, controlled studies are warranted to corroborate our results.

Preservation of Cerebellar Afferent Pathway May Be Related to Good Hand Function in Patients with Stroke.

Many chronic stroke patients suffer from worsened hand function, and functional recovery of the hand does not occur well after six months of stroke. Therefore, predicting final hand function after stroke through acute phase imaging would be an important issue in counseling with the patients or their family. Thus, we investigated the remaining white matter integrity in the corticospinal tract (CST) and cortico-ponto-cerebellar tract (CPCT) at the acute stage of stroke and chronic hand function after stroke, and present the cut-off value of fiber number (FN) and fractional anisotropy (FA) of CST and CPCT at the acute stage for predicting final hand function after the recovery period. This retrospective case-control study included 18 stroke patients who were classified into two groups: poor hand function with stroke (n = 11) and good hand function with stroke (n = 7). DTI was done within two months ± 15 days after onset, and the Jebson's Hand Function test was conducted 6-12 months after onset. The investigation of white matter was focused on the values of FN and FA for CST and CPCT, which were measured separately. The normalized (affected/non-affected) FA and FN values in the CPCT in the good hand function group were higher than those in the poor hand function group. The normalized FN and FA values in the CST were not significantly different between the poor hand function group and the good hand function group. The normalized cut-off value that distinguished the good hand function group from the poor hand function group was 0.8889 for FA in the CPCT. The integrity of the CPCT in the acute stage was associated with hand function in the chronic stage after a stroke. Ultimately, the integrity of the CPCT in the early stage after onset can be used to predict chronic hand function. Based on these results, cerebellar afferent fiber measurements may be a useful addition to predict hand function and plan specific rehabilitation strategies in stroke patients.