Determining the effects of targeted high-definition transcranial direct current stimulation on reducing post-stroke upper limb motor impairments-a randomized cross-over study.

BACKGROUND: Stroke is one of the leading causes of death in the USA and is a major cause of serious disability for adults. This randomized crossover study examines the effect of targeted high-definition transcranial direct current transcranial brain stimulation (tDCS) on upper extremity motor recovery in patients in the post-acute phase of stroke recovery. METHODS: This randomized double-blinded cross-over study includes four intervention arms: anodal, cathodal, and bilateral brain stimulation, as well as a placebo stimulation. Participants receive each intervention in a randomized order, with a 2-week washout period between each intervention. The primary outcome measure is change in Motor Evoked Potential. Secondary outcome measures include the Fugl-Meyer Upper Extremity (FM-UE) score, a subset of FM-UE (A), related to the muscle synergies, and the Modified Ashworth Scale. DISCUSSION: We hypothesize that anodal stimulation to the ipsilesional primary motor cortex will increase the excitability of the damaged cortico-spinal tract, reducing the UE flexion synergy and enhancing UE motor function. We further hypothesize that targeted cathodal stimulation to the contralesional premotor cortex will decrease activation of the cortico-reticulospinal tract (CRST) and the expression of the upper extremity (UE) flexion synergy and spasticity. Finally, we hypothesize bilateral stimulation will achieve both results simultaneously. Results from this study could improve understanding of the mechanism behind motor impairment and recovery in stroke and perfect the targeting of tDCS as a potential stroke intervention. With the use of appropriate screening, we anticipate no ethical or safety concerns. We plan to disseminate these research results to journals related to stroke recovery, engineering, and medicine. TRIAL REGISTRATION: ClinicalTrials.gov NCT05479006 . Registered on 26 July 2022.

Artificial Intelligence for Early Detection of Chest Nodules in X-ray Images.

Early detection increases overall survival among patients with lung cancer. This study formulated a machine learning method that processes chest X-rays (CXRs) to detect lung cancer early. After we preprocessed our dataset using monochrome and brightness correction, we used different kinds of preprocessing methods to enhance image contrast and then used U-net to perform lung segmentation. We used 559 CXRs with a single lung nodule labeled by experts to train a You Only Look Once version 4 (YOLOv4) deep-learning architecture to detect lung nodules. In a testing dataset of 100 CXRs from patients at Taipei Veterans General Hospital and 154 CXRs from the Japanese Society of Radiological Technology dataset, the sensitivity of the AI model using a combination of different preprocessing methods performed the best at 79%, with 3.04 false positives per image. We then tested the AI by using 383 sets of CXRs obtained in the past 5 years prior to lung cancer diagnoses. The median time from detection to diagnosis for radiologists assisted with AI was 46 (3-523) days, longer than that for radiologists (8 (0-263) days). The AI model can assist radiologists in the early detection of lung nodules.